update
Browse files- app.py +30 -23
- src/results/models_2024-10-07-14:50:12.666068.jsonl +0 -677
- src/results/models_2024-10-08-03:10:26.811832.jsonl +0 -1770
- src/results/models_2024-10-08-03:25:44.801310.jsonl +0 -2082
- src/results/models_2024-10-08-17:39:21.001582.jsonl +0 -2082
- src/results/models_2024-10-09-05:17:38.810960.json +0 -2327
- src/results/models_2024-10-09-06:22:21.122422.json +0 -2372
- src/results/models_2024-10-10-06:18:54.263527.json +0 -2622
- src/results/models_2024-10-18-14:06:13.588399.json +0 -2732
- src/results/{models_2024-10-20-23:34:57.242641.json → models_2024-10-24-08:08:59.127307.json} +0 -0
app.py
CHANGED
|
@@ -99,15 +99,8 @@ def init_leaderboard(dataframe):
|
|
| 99 |
interactive=False,
|
| 100 |
)
|
| 101 |
|
| 102 |
-
# model_result_path = "./src/results/models_2024-10-
|
| 103 |
-
|
| 104 |
-
# model_result_path = "./src/results/models_2024-10-08-03:25:44.801310.jsonl"
|
| 105 |
-
# model_result_path = "./src/results/models_2024-10-08-17:39:21.001582.jsonl"
|
| 106 |
-
# model_result_path = "./src/results/models_2024-10-09-05:17:38.810960.json"
|
| 107 |
-
# model_result_path = "./src/results/models_2024-10-09-06:22:21.122422.json"
|
| 108 |
-
# model_result_path = "./src/results/models_2024-10-10-06:18:54.263527.json"
|
| 109 |
-
# model_result_path = "./src/results/models_2024-10-18-14:06:13.588399.json"
|
| 110 |
-
model_result_path = "./src/results/models_2024-10-20-23:34:57.242641.json"
|
| 111 |
# model_leaderboard_df = get_model_leaderboard_df(model_result_path)
|
| 112 |
|
| 113 |
|
|
@@ -267,22 +260,36 @@ with demo:
|
|
| 267 |
|
| 268 |
|
| 269 |
with gr.TabItem("🔢 Math", elem_id="math-tab-table", id=2):
|
| 270 |
-
DESCRIPTION_TEXT="""
|
| 271 |
-
Algebra, Geometry, and Probability are the current three main math domains in the leaderboard.
|
| 272 |
-
To mitigate the potential impact of data contimination, we have carefully selected the datasets from various sources.
|
| 273 |
-
We prioritize **recent math datasets** and focus on **college and beyond level** math questions.
|
| 274 |
-
The current datasets include
|
| 275 |
-
[MATH](https://arxiv.org/abs/2103.03874),
|
| 276 |
-
[MATH-500](https://github.com/openai/prm800k/tree/main/prm800k/math_splits),
|
| 277 |
-
[Omni](https://omni-math.github.io/),
|
| 278 |
-
[MathQA](https://arxiv.org/abs/1905.13319),
|
| 279 |
-
[MathBench](https://arxiv.org/abs/2405.12209),
|
| 280 |
-
[SciBench](https://arxiv.org/abs/2307.10635), and more!
|
| 281 |
|
| 282 |
-
We plan to include more math domains, such as calculus, number theory, and more in the future.
|
| 283 |
-
"""
|
| 284 |
-
gr.Markdown(DESCRIPTION_TEXT, elem_classes="markdown-text")
|
| 285 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 286 |
# leaderboard = init_leaderboard(LEADERBOARD_DF)
|
| 287 |
with gr.TabItem("🏆 Overview", elem_id="math_overview_subtab", id=0, elem_classes="subtab"):
|
| 288 |
|
|
|
|
| 99 |
interactive=False,
|
| 100 |
)
|
| 101 |
|
| 102 |
+
# model_result_path = "./src/results/models_2024-10-20-23:34:57.242641.json"
|
| 103 |
+
model_result_path = "./src/results/models_2024-10-24-08:08:59.127307.json"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
# model_leaderboard_df = get_model_leaderboard_df(model_result_path)
|
| 105 |
|
| 106 |
|
|
|
|
| 260 |
|
| 261 |
|
| 262 |
with gr.TabItem("🔢 Math", elem_id="math-tab-table", id=2):
|
| 263 |
+
# DESCRIPTION_TEXT="""
|
| 264 |
+
# Algebra, Geometry, and Probability are the current three main math domains in the leaderboard.
|
| 265 |
+
# To mitigate the potential impact of data contimination, we have carefully selected the datasets from various sources.
|
| 266 |
+
# We prioritize **recent math datasets** and focus on **college and beyond level** math questions.
|
| 267 |
+
# The current datasets include
|
| 268 |
+
# [MATH](https://arxiv.org/abs/2103.03874),
|
| 269 |
+
# [MATH-500](https://github.com/openai/prm800k/tree/main/prm800k/math_splits),
|
| 270 |
+
# [Omni](https://omni-math.github.io/),
|
| 271 |
+
# [MathQA](https://arxiv.org/abs/1905.13319),
|
| 272 |
+
# [MathBench](https://arxiv.org/abs/2405.12209),
|
| 273 |
+
# [SciBench](https://arxiv.org/abs/2307.10635), and more!
|
| 274 |
|
| 275 |
+
# We plan to include more math domains, such as calculus, number theory, and more in the future.
|
| 276 |
+
# """
|
| 277 |
+
# gr.Markdown(DESCRIPTION_TEXT, elem_classes="markdown-text")
|
| 278 |
|
| 279 |
+
TEXT = (
|
| 280 |
+
f'<p style="font-size:{INTRODUCTION_TEXT_FONT_SIZE}px;">'
|
| 281 |
+
'<b>Total #models: 57 (Last updated: 2024-10-21)</b>'
|
| 282 |
+
'</p>'
|
| 283 |
+
f'<p style="font-size:{INTRODUCTION_TEXT_FONT_SIZE}px;">'
|
| 284 |
+
'This page prvovides a comprehensive overview of model ranks across various dimensions, based on their averaged ranks or scores.'
|
| 285 |
+
'(Missing values are due to the slow or problemtic model responses to be fixed soom.)'
|
| 286 |
+
'</p>'
|
| 287 |
+
# '<p style="font-size:{INTRODUCTION_TEXT_FONT_SIZE}px;">'
|
| 288 |
+
# 'We present '
|
| 289 |
+
# '</p>'
|
| 290 |
+
)
|
| 291 |
+
gr.HTML(TEXT)
|
| 292 |
+
|
| 293 |
# leaderboard = init_leaderboard(LEADERBOARD_DF)
|
| 294 |
with gr.TabItem("🏆 Overview", elem_id="math_overview_subtab", id=0, elem_classes="subtab"):
|
| 295 |
|
src/results/models_2024-10-07-14:50:12.666068.jsonl
DELETED
|
@@ -1,677 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{"config": {
|
| 3 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 4 |
-
"organization": "OpenAI",
|
| 5 |
-
"license": "Proprietary",
|
| 6 |
-
"knowledge_cutoff": "2023/10"
|
| 7 |
-
},
|
| 8 |
-
"results": {
|
| 9 |
-
"math-algebra": {"Score": 99.19484702, "Avg Rank": 1.666666667, "Min Rank": 1, "Max Rank": 3},
|
| 10 |
-
"math-probability": {"Score": 100, "Avg Rank": 1, "Min Rank": 1, "Max Rank": 1},
|
| 11 |
-
"reasoning-logical": {"Avg Rank": 1, "Min Rank": 1, "Max Rank": 1},
|
| 12 |
-
"overall": {"Avg Rank": 2, "Min Rank": 2, "Max Rank": 2}
|
| 13 |
-
}},
|
| 14 |
-
|
| 15 |
-
{"config": {
|
| 16 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 17 |
-
"organization": "OpenAI",
|
| 18 |
-
"license": "Proprietary",
|
| 19 |
-
"knowledge_cutoff": "2023/10"
|
| 20 |
-
},
|
| 21 |
-
"results": {
|
| 22 |
-
"math-algebra": {"Score": 98.38969404, "Avg Rank": 1.666666667, "Min Rank": 1, "Max Rank": 2},
|
| 23 |
-
"math-probability": {"Score": 96.49758454, "Avg Rank": 2.666666667, "Min Rank": 2, "Max Rank": 4},
|
| 24 |
-
"reasoning-logical": {"Avg Rank": 4.333333333, "Min Rank": 3, "Max Rank": 5},
|
| 25 |
-
"overall": {"Avg Rank": 7.33, "Min Rank": 4, "Max Rank": 9}
|
| 26 |
-
}},
|
| 27 |
-
|
| 28 |
-
{"config": {
|
| 29 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 30 |
-
"organization": "OpenAI",
|
| 31 |
-
"license": "Proprietary",
|
| 32 |
-
"knowledge_cutoff": "2023/10"
|
| 33 |
-
},
|
| 34 |
-
"results": {
|
| 35 |
-
"math-algebra": {"Score": 98.15480333, "Avg Rank": 2.666666667, "Min Rank": 2, "Max Rank": 3},
|
| 36 |
-
"math-probability": {"Score": 94.83939431, "Avg Rank": 3.666666667, "Min Rank": 2, "Max Rank": 5},
|
| 37 |
-
"reasoning-logical": {"Avg Rank": 6.333333333, "Min Rank": 3, "Max Rank": 8},
|
| 38 |
-
"overall": {"Avg Rank": 7.67, "Min Rank": 7, "Max Rank": 9}
|
| 39 |
-
}},
|
| 40 |
-
|
| 41 |
-
{"config": {
|
| 42 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 43 |
-
"organization": "OpenAI",
|
| 44 |
-
"license": "Proprietary",
|
| 45 |
-
"knowledge_cutoff": "2023/12"
|
| 46 |
-
},
|
| 47 |
-
"results": {
|
| 48 |
-
"math-algebra": {"Score": 96.03195879, "Avg Rank": 4, "Min Rank": 4, "Max Rank": 4},
|
| 49 |
-
"math-probability": {"Score": 93.59903382, "Avg Rank": 6.666666667, "Min Rank": 6, "Max Rank": 8},
|
| 50 |
-
"reasoning-logical": {"Avg Rank": 4, "Min Rank": 2, "Max Rank": 7},
|
| 51 |
-
"overall": {"Avg Rank": 6, "Min Rank": 5, "Max Rank": 8}
|
| 52 |
-
}},
|
| 53 |
-
|
| 54 |
-
{"config": {
|
| 55 |
-
"model_name": "gemini-1.5-pro-001",
|
| 56 |
-
"organization": "Google",
|
| 57 |
-
"license": "Proprietary",
|
| 58 |
-
"knowledge_cutoff": "2024-01"
|
| 59 |
-
},
|
| 60 |
-
"results": {
|
| 61 |
-
"math-algebra": {"Score": 94.7572213, "Avg Rank": 5, "Min Rank": 5, "Max Rank": 5},
|
| 62 |
-
"math-probability": {"Score": 91.42512077, "Avg Rank": 9.666666667, "Min Rank": 9, "Max Rank": 10},
|
| 63 |
-
"reasoning-logical": {"Avg Rank": 9.666666667, "Min Rank": 9, "Max Rank": 11},
|
| 64 |
-
"overall": {"Avg Rank": 14, "Min Rank": 13, "Max Rank": 15}
|
| 65 |
-
}},
|
| 66 |
-
|
| 67 |
-
{"config": {
|
| 68 |
-
"model_name": "qwen2-72b-instruct",
|
| 69 |
-
"organization": "Alibaba",
|
| 70 |
-
"license": "Qianwen LICENSE",
|
| 71 |
-
"knowledge_cutoff": "2024-02"
|
| 72 |
-
},
|
| 73 |
-
"results": {
|
| 74 |
-
"math-algebra": {"Score": 93.88818605, "Avg Rank": 6, "Min Rank": 6, "Max Rank": 6},
|
| 75 |
-
"math-probability": {"Score": 91.54326174, "Avg Rank": 4, "Min Rank": 3, "Max Rank": 5},
|
| 76 |
-
"reasoning-logical": {"Avg Rank": 15.66666667, "Min Rank": 15, "Max Rank": 17},
|
| 77 |
-
"overall": {"Avg Rank": 17, "Min Rank": 17, "Max Rank": 17}
|
| 78 |
-
}},
|
| 79 |
-
|
| 80 |
-
{"config": {
|
| 81 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 82 |
-
"organization": "OpenAI",
|
| 83 |
-
"license": "Proprietary",
|
| 84 |
-
"knowledge_cutoff": "2024-07"
|
| 85 |
-
},
|
| 86 |
-
"results": {
|
| 87 |
-
"math-algebra": {"Score": 93.22073596, "Avg Rank": 7, "Min Rank": 7, "Max Rank": 7},
|
| 88 |
-
"math-probability": {"Score": 92.17351456, "Avg Rank": 3.666666667, "Min Rank": 3, "Max Rank": 5},
|
| 89 |
-
"reasoning-logical": {"Avg Rank": 9.666666667, "Min Rank": 9, "Max Rank": 10},
|
| 90 |
-
"overall": {"Avg Rank": 7, "Min Rank": 5, "Max Rank": 8}
|
| 91 |
-
}},
|
| 92 |
-
|
| 93 |
-
{"config": {
|
| 94 |
-
"model_name": "claude-3.5-sonnet",
|
| 95 |
-
"organization": "Anthropic",
|
| 96 |
-
"license": "Proprietary",
|
| 97 |
-
"knowledge_cutoff": "2024-03"
|
| 98 |
-
},
|
| 99 |
-
"results": {
|
| 100 |
-
"math-algebra": {"Score": 91.5823805, "Avg Rank": 8.333333333, "Min Rank": 8, "Max Rank": 9},
|
| 101 |
-
"math-probability": {"Score": 91.55011915, "Avg Rank": 8, "Min Rank": 7, "Max Rank": 9},
|
| 102 |
-
"reasoning-logical": {"Avg Rank": 5, "Min Rank": 2, "Max Rank": 7},
|
| 103 |
-
"overall": {"Avg Rank": 5, "Min Rank": 4, "Max Rank": 7}
|
| 104 |
-
}},
|
| 105 |
-
|
| 106 |
-
{"config": {
|
| 107 |
-
"model_name": "o1-mini",
|
| 108 |
-
"organization": "01 AI",
|
| 109 |
-
"license": "Proprietary",
|
| 110 |
-
"knowledge_cutoff": "2024-01"
|
| 111 |
-
},
|
| 112 |
-
"results": {
|
| 113 |
-
"math-algebra": None,
|
| 114 |
-
"math-probability": None,
|
| 115 |
-
"reasoning-logical": None,
|
| 116 |
-
"overall": {"Avg Rank": 1, "Min Rank": 1, "Max Rank": 1}
|
| 117 |
-
}},
|
| 118 |
-
|
| 119 |
-
{"config": {
|
| 120 |
-
"model_name": "o1-preview",
|
| 121 |
-
"organization": "01 AI",
|
| 122 |
-
"license": "Proprietary",
|
| 123 |
-
"knowledge_cutoff": "2024-01"
|
| 124 |
-
},
|
| 125 |
-
"results": {
|
| 126 |
-
"math-algebra": None,
|
| 127 |
-
"math-probability": None,
|
| 128 |
-
"reasoning-logical": None,
|
| 129 |
-
"overall": {"Avg Rank": 3, "Min Rank": 3, "Max Rank": 3}
|
| 130 |
-
}},
|
| 131 |
-
|
| 132 |
-
{"config": {
|
| 133 |
-
"model_name": "gemini-1.5-flash-001",
|
| 134 |
-
"organization": "Google",
|
| 135 |
-
"license": "Proprietary",
|
| 136 |
-
"knowledge_cutoff": "2024-02"
|
| 137 |
-
},
|
| 138 |
-
"results": {
|
| 139 |
-
"math-algebra": {"Score": 91.30211121, "Avg Rank": 11, "Min Rank": 11, "Max Rank": 11},
|
| 140 |
-
"math-probability": {"Score": 91.066099, "Avg Rank": 12, "Min Rank": 10, "Max Rank": 13},
|
| 141 |
-
"reasoning-logical": {"Avg Rank": 15.66666667, "Min Rank": 15, "Max Rank": 16},
|
| 142 |
-
"overall": {"Avg Rank": 14, "Min Rank": 13, "Max Rank": 15}
|
| 143 |
-
}},
|
| 144 |
-
|
| 145 |
-
{"config": {
|
| 146 |
-
"model_name": "gpt4-1106",
|
| 147 |
-
"organization": "OpenAI",
|
| 148 |
-
"license": "Proprietary",
|
| 149 |
-
"knowledge_cutoff": "2024-04"
|
| 150 |
-
},
|
| 151 |
-
"results": {
|
| 152 |
-
"math-algebra": {"Score": 91.2227739, "Avg Rank": 12, "Min Rank": 12, "Max Rank": 12},
|
| 153 |
-
"math-probability": {"Score": 91.09550085, "Avg Rank": 11.66666667, "Min Rank": 11, "Max Rank": 12},
|
| 154 |
-
"reasoning-logical": {"Avg Rank": 12, "Min Rank": 12, "Max Rank": 12},
|
| 155 |
-
"overall": {"Avg Rank": 12, "Min Rank": 11, "Max Rank": 12}
|
| 156 |
-
}},
|
| 157 |
-
|
| 158 |
-
{"config": {
|
| 159 |
-
"model_name": "gemma-2-27b-it",
|
| 160 |
-
"organization": "Google",
|
| 161 |
-
"license": "Gemma License",
|
| 162 |
-
"knowledge_cutoff": "2024-03"
|
| 163 |
-
},
|
| 164 |
-
"results": {
|
| 165 |
-
"math-algebra": {"Score": 91.08554346, "Avg Rank": 13.33333333, "Min Rank": 13, "Max Rank": 14},
|
| 166 |
-
"math-probability": {"Score": 91.09516215, "Avg Rank": 14, "Min Rank": 14, "Max Rank": 14},
|
| 167 |
-
"reasoning-logical": {"Avg Rank": 13, "Min Rank": 13, "Max Rank": 13},
|
| 168 |
-
"overall": {"Avg Rank": 13, "Min Rank": 12, "Max Rank": 14}
|
| 169 |
-
}},
|
| 170 |
-
|
| 171 |
-
{"config": {
|
| 172 |
-
"model_name": "claude-3-opus",
|
| 173 |
-
"organization": "Anthropic",
|
| 174 |
-
"license": "Proprietary",
|
| 175 |
-
"knowledge_cutoff": "2024-01"
|
| 176 |
-
},
|
| 177 |
-
"results": {
|
| 178 |
-
"math-algebra": {"Score": 89.75345785, "Avg Rank": 13.66666667, "Min Rank": 13, "Max Rank": 14},
|
| 179 |
-
"math-probability": {"Score": 91.06939607, "Avg Rank": 11.33333333, "Min Rank": 11, "Max Rank": 12},
|
| 180 |
-
"reasoning-logical": {"Avg Rank": 10.66666667, "Min Rank": 10, "Max Rank": 11},
|
| 181 |
-
"overall": {"Avg Rank": 12, "Min Rank": 10, "Max Rank": 15}
|
| 182 |
-
}},
|
| 183 |
-
|
| 184 |
-
{"config": {
|
| 185 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 186 |
-
"organization": "Google",
|
| 187 |
-
"license": "Gemma License",
|
| 188 |
-
"knowledge_cutoff": "2024-02"
|
| 189 |
-
},
|
| 190 |
-
"results": {
|
| 191 |
-
"math-algebra": {"Score": 87.66368227, "Avg Rank": 15, "Min Rank": 15, "Max Rank": 15},
|
| 192 |
-
"math-probability": {"Score": 73.64665336, "Avg Rank": 17, "Min Rank": 17, "Max Rank": 17},
|
| 193 |
-
"reasoning-logical": {"Avg Rank": 19, "Min Rank": 19, "Max Rank": 19},
|
| 194 |
-
"overall": {"Avg Rank": 17, "Min Rank": 15, "Max Rank": 19}
|
| 195 |
-
}},
|
| 196 |
-
|
| 197 |
-
{"config": {
|
| 198 |
-
"model_name": "qwen1.5-72b-chat",
|
| 199 |
-
"organization": "Alibaba",
|
| 200 |
-
"license": "Qianwen LICENSE",
|
| 201 |
-
"knowledge_cutoff": "2024-03"
|
| 202 |
-
},
|
| 203 |
-
"results": {
|
| 204 |
-
"math-algebra": {"Score": 86.56207015, "Avg Rank": 16, "Min Rank": 16, "Max Rank": 16},
|
| 205 |
-
"math-probability": {"Score": 72.7735874, "Avg Rank": 21, "Min Rank": 20, "Max Rank": 22},
|
| 206 |
-
"reasoning-logical": {"Avg Rank": 29.66666667, "Min Rank": 28, "Max Rank": 31},
|
| 207 |
-
"overall": {"Avg Rank": 23, "Min Rank": 16, "Max Rank": 31}
|
| 208 |
-
}},
|
| 209 |
-
|
| 210 |
-
{"config": {
|
| 211 |
-
"model_name": "qwen1.5-32b-chat",
|
| 212 |
-
"organization": "Alibaba",
|
| 213 |
-
"license": "Qianwen LICENSE",
|
| 214 |
-
"knowledge_cutoff": "2024-03"
|
| 215 |
-
},
|
| 216 |
-
"results": {
|
| 217 |
-
"math-algebra": {"Score": 84.59439036, "Avg Rank": 17.33333333, "Min Rank": 17, "Max Rank": 18},
|
| 218 |
-
"math-probability": {"Score": 76.61348265, "Avg Rank": 22.33333333, "Min Rank": 22, "Max Rank": 23},
|
| 219 |
-
"reasoning-logical": {"Avg Rank": 28.66666667, "Min Rank": 27, "Max Rank": 30},
|
| 220 |
-
"overall": {"Avg Rank": 22, "Min Rank": 17, "Max Rank": 30}
|
| 221 |
-
}},
|
| 222 |
-
|
| 223 |
-
{"config": {
|
| 224 |
-
"model_name": "google-gemma-2-9b-it",
|
| 225 |
-
"organization": "Google",
|
| 226 |
-
"license": "Proprietary",
|
| 227 |
-
"knowledge_cutoff": "2024-01"
|
| 228 |
-
},
|
| 229 |
-
"results": {
|
| 230 |
-
"math-algebra": {"Score": 84.18901776, "Avg Rank": 18, "Min Rank": 17, "Max Rank": 19},
|
| 231 |
-
"math-probability": {"Score": 74.46332504, "Avg Rank": 16, "Min Rank": 16, "Max Rank": 16},
|
| 232 |
-
"reasoning-logical": {"Avg Rank": 14, "Min Rank": 14, "Max Rank": 14},
|
| 233 |
-
"overall": {"Avg Rank": 16, "Min Rank": 14, "Max Rank": 19}
|
| 234 |
-
}},
|
| 235 |
-
|
| 236 |
-
{"config": {
|
| 237 |
-
"model_name": "yi-1.5-34b-chat",
|
| 238 |
-
"organization": "01 AI",
|
| 239 |
-
"license": "Proprietary",
|
| 240 |
-
"knowledge_cutoff": "2024-01"
|
| 241 |
-
},
|
| 242 |
-
"results": {
|
| 243 |
-
"math-algebra": {"Score": 81.82921677, "Avg Rank": 18.66666667, "Min Rank": 18, "Max Rank": 19},
|
| 244 |
-
"math-probability": {"Score": 77.41945842, "Avg Rank": 15, "Min Rank": 15, "Max Rank": 15},
|
| 245 |
-
"reasoning-logical": {"Avg Rank": 17.33333333, "Min Rank": 17, "Max Rank": 18},
|
| 246 |
-
"overall": {"Avg Rank": 18, "Min Rank": 15, "Max Rank": 19}
|
| 247 |
-
}},
|
| 248 |
-
|
| 249 |
-
{"config": {
|
| 250 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 251 |
-
"organization": "Meta",
|
| 252 |
-
"license": "Llama 3.1 Community",
|
| 253 |
-
"knowledge_cutoff": "2024-02"
|
| 254 |
-
},
|
| 255 |
-
"results": {
|
| 256 |
-
"math-algebra": {"Score": 75.57121963, "Avg Rank": 20.33333333, "Min Rank": 20, "Max Rank": 21},
|
| 257 |
-
"math-probability": {"Score": 75.46243493, "Avg Rank": 20.33333333, "Min Rank": 20, "Max Rank": 21},
|
| 258 |
-
"reasoning-logical": {"Avg Rank": 23.66666667, "Min Rank": 23, "Max Rank": 24},
|
| 259 |
-
"overall": {"Avg Rank": 21, "Min Rank": 20, "Max Rank": 24}
|
| 260 |
-
}},
|
| 261 |
-
|
| 262 |
-
{"config": {
|
| 263 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 264 |
-
"organization": "OpenAI",
|
| 265 |
-
"license": "Proprietary",
|
| 266 |
-
"knowledge_cutoff": "2023-12"
|
| 267 |
-
},
|
| 268 |
-
"results": {
|
| 269 |
-
"math-algebra": {"Score": 73.29235048, "Avg Rank": 21.33333333, "Min Rank": 21, "Max Rank": 22},
|
| 270 |
-
"math-probability": {"Score": 66.27452275, "Avg Rank": 24, "Min Rank": 24, "Max Rank": 24},
|
| 271 |
-
"reasoning-logical": {"Avg Rank": 42.66666667, "Min Rank": 42, "Max Rank": 44},
|
| 272 |
-
"overall": {"Avg Rank": 29, "Min Rank": 21, "Max Rank": 44}
|
| 273 |
-
}},
|
| 274 |
-
|
| 275 |
-
{"config": {
|
| 276 |
-
"model_name": "llama-3-70b-instruct",
|
| 277 |
-
"organization": "Meta",
|
| 278 |
-
"license": "Llama 3 Community",
|
| 279 |
-
"knowledge_cutoff": "2024-03"
|
| 280 |
-
},
|
| 281 |
-
"results": {
|
| 282 |
-
"math-algebra": {"Score": 73.75419539, "Avg Rank": 21.33333333, "Min Rank": 20, "Max Rank": 22},
|
| 283 |
-
"math-probability": {"Score": 87.86358478, "Avg Rank": 18.33333333, "Min Rank": 18, "Max Rank": 19},
|
| 284 |
-
"reasoning-logical": {"Avg Rank": 3.333333333, "Min Rank": 2, "Max Rank": 4},
|
| 285 |
-
"overall": {"Avg Rank": 15, "Min Rank": 3, "Max Rank": 22}
|
| 286 |
-
}},
|
| 287 |
-
|
| 288 |
-
{"config": {
|
| 289 |
-
"model_name": "claude-3-sonnet",
|
| 290 |
-
"organization": "Anthropic",
|
| 291 |
-
"license": "Proprietary",
|
| 292 |
-
"knowledge_cutoff": "2024-02"
|
| 293 |
-
},
|
| 294 |
-
"results": {
|
| 295 |
-
"math-algebra": {"Score": 71.15353833, "Avg Rank": 23, "Min Rank": 23, "Max Rank": 23},
|
| 296 |
-
"math-probability": {"Score": 88.02362801, "Avg Rank": 18.66666667, "Min Rank": 18, "Max Rank": 19},
|
| 297 |
-
"reasoning-logical": {"Avg Rank": 17.33333333, "Min Rank": 16, "Max Rank": 18},
|
| 298 |
-
"overall": {"Avg Rank": 20, "Min Rank": 16, "Max Rank": 23}
|
| 299 |
-
}},
|
| 300 |
-
|
| 301 |
-
{"config": {
|
| 302 |
-
"model_name": "qwen1.5-14b-chat",
|
| 303 |
-
"organization": "Alibaba",
|
| 304 |
-
"license": "Qianwen LICENSE",
|
| 305 |
-
"knowledge_cutoff": "2024-01"
|
| 306 |
-
},
|
| 307 |
-
"results": {
|
| 308 |
-
"math-algebra": {"Score": 69.70470323, "Avg Rank": 24, "Min Rank": 24, "Max Rank": 24},
|
| 309 |
-
"math-probability": {"Score": 66.41420544, "Avg Rank": 28.66666667, "Min Rank": 28, "Max Rank": 29},
|
| 310 |
-
"reasoning-logical": {"Avg Rank": 34, "Min Rank": 34, "Max Rank": 34},
|
| 311 |
-
"overall": {"Avg Rank": 28, "Min Rank": 24, "Max Rank": 34}
|
| 312 |
-
}},
|
| 313 |
-
|
| 314 |
-
{"config": {
|
| 315 |
-
"model_name": "claude-3-haiku",
|
| 316 |
-
"organization": "Anthropic",
|
| 317 |
-
"license": "Proprietary",
|
| 318 |
-
"knowledge_cutoff": "2024-01"
|
| 319 |
-
},
|
| 320 |
-
"results": {
|
| 321 |
-
"math-algebra": {"Score": 68.44060149, "Avg Rank": 25, "Min Rank": 25, "Max Rank": 25},
|
| 322 |
-
"math-probability": {"Score": 76.46075239, "Avg Rank": 22.33333333, "Min Rank": 21, "Max Rank": 23},
|
| 323 |
-
"reasoning-logical": {"Avg Rank": 20, "Min Rank": 20, "Max Rank": 20},
|
| 324 |
-
"overall": {"Avg Rank": 22, "Min Rank": 20, "Max Rank": 25}
|
| 325 |
-
}},
|
| 326 |
-
|
| 327 |
-
{"config": {
|
| 328 |
-
"model_name": "claude-2.1",
|
| 329 |
-
"organization": "Anthropic",
|
| 330 |
-
"license": "Proprietary",
|
| 331 |
-
"knowledge_cutoff": "2023-12"
|
| 332 |
-
},
|
| 333 |
-
"results": {
|
| 334 |
-
"math-algebra": {"Score": 67.59939121, "Avg Rank": 26, "Min Rank": 26, "Max Rank": 26},
|
| 335 |
-
"math-probability": {"Score": 68.89772398, "Avg Rank": 27, "Min Rank": 27, "Max Rank": 27},
|
| 336 |
-
"reasoning-logical": {"Avg Rank": 21, "Min Rank": 21, "Max Rank": 21},
|
| 337 |
-
"overall": {"Avg Rank": 25, "Min Rank": 21, "Max Rank": 27}
|
| 338 |
-
}},
|
| 339 |
-
|
| 340 |
-
{"config": {
|
| 341 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 342 |
-
"organization": "Mistral",
|
| 343 |
-
"license": "Apache 2.0",
|
| 344 |
-
"knowledge_cutoff": "2023-12"
|
| 345 |
-
},
|
| 346 |
-
"results": {
|
| 347 |
-
"math-algebra": {"Score": 64.71364004, "Avg Rank": 27, "Min Rank": 27, "Max Rank": 27},
|
| 348 |
-
"math-probability": {"Score": 67.67468595, "Avg Rank": 26, "Min Rank": 26, "Max Rank": 26},
|
| 349 |
-
"reasoning-logical": {"Avg Rank": 29, "Min Rank": 28, "Max Rank": 30},
|
| 350 |
-
"overall": {"Avg Rank": 27, "Min Rank": 26, "Max Rank": 30}
|
| 351 |
-
}},
|
| 352 |
-
|
| 353 |
-
{"config": {
|
| 354 |
-
"model_name": "claude-2.0",
|
| 355 |
-
"organization": "Anthropic",
|
| 356 |
-
"license": "Proprietary",
|
| 357 |
-
"knowledge_cutoff": "2023-10"
|
| 358 |
-
},
|
| 359 |
-
"results": {
|
| 360 |
-
"math-algebra": {"Score": 64.77311289, "Avg Rank": 28, "Min Rank": 28, "Max Rank": 28},
|
| 361 |
-
"math-probability": {"Score": 74.34063069, "Avg Rank": 25, "Min Rank": 25, "Max Rank": 25},
|
| 362 |
-
"reasoning-logical": {"Avg Rank": 23.33333333, "Min Rank": 23, "Max Rank": 24},
|
| 363 |
-
"overall": {"Avg Rank": 25, "Min Rank": 23, "Max Rank": 28}
|
| 364 |
-
}},
|
| 365 |
-
|
| 366 |
-
{"config": {
|
| 367 |
-
"model_name": "starling-lm-7b-beta",
|
| 368 |
-
"organization": "Nexusflow",
|
| 369 |
-
"license": "Apache-2.0",
|
| 370 |
-
"knowledge_cutoff": "2024-01"
|
| 371 |
-
},
|
| 372 |
-
"results": {
|
| 373 |
-
"math-algebra": {"Score": 64.01222884, "Avg Rank": 29.33333333, "Min Rank": 29, "Max Rank": 30},
|
| 374 |
-
"math-probability": {"Score": 70.42025806, "Avg Rank": 28.33333333, "Min Rank": 28, "Max Rank": 29},
|
| 375 |
-
"reasoning-logical": {"Avg Rank": 25, "Min Rank": 25, "Max Rank": 25},
|
| 376 |
-
"overall": {"Avg Rank": 27, "Min Rank": 25, "Max Rank": 30}
|
| 377 |
-
}},
|
| 378 |
-
|
| 379 |
-
{"config": {
|
| 380 |
-
"model_name": "gemini-1.0-pro-001",
|
| 381 |
-
"organization": "Google",
|
| 382 |
-
"license": "Proprietary",
|
| 383 |
-
"knowledge_cutoff": "2023-11"
|
| 384 |
-
},
|
| 385 |
-
"results": {
|
| 386 |
-
"math-algebra": {"Score": 63.93365247, "Avg Rank": 29.66666667, "Min Rank": 29, "Max Rank": 30},
|
| 387 |
-
"math-probability": {"Score": 62.13077748, "Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 38},
|
| 388 |
-
"reasoning-logical": {"Avg Rank": 37.33333333, "Min Rank": 36, "Max Rank": 40},
|
| 389 |
-
"overall": {"Avg Rank": 34, "Min Rank": 29, "Max Rank": 40}
|
| 390 |
-
}},
|
| 391 |
-
|
| 392 |
-
{"config": {
|
| 393 |
-
"model_name": "openchat-3.5-0106",
|
| 394 |
-
"organization": "OpenChat",
|
| 395 |
-
"license": "Apache-2.0",
|
| 396 |
-
"knowledge_cutoff": "2024-01"
|
| 397 |
-
},
|
| 398 |
-
"results": {
|
| 399 |
-
"math-algebra": {"Score": 63.02959506, "Avg Rank": 31, "Min Rank": 31, "Max Rank": 31},
|
| 400 |
-
"math-probability": {"Score": 61.00599665, "Avg Rank": 30, "Min Rank": 30, "Max Rank": 30},
|
| 401 |
-
"reasoning-logical": {"Avg Rank": 27.66666667, "Min Rank": 27, "Max Rank": 29},
|
| 402 |
-
"overall": {"Avg Rank": 29, "Min Rank": 27, "Max Rank": 31}
|
| 403 |
-
}},
|
| 404 |
-
|
| 405 |
-
{"config": {
|
| 406 |
-
"model_name": "openchat-3.5",
|
| 407 |
-
"organization": "OpenChat",
|
| 408 |
-
"license": "Apache-2.0",
|
| 409 |
-
"knowledge_cutoff": "2023-12"
|
| 410 |
-
},
|
| 411 |
-
"results": {
|
| 412 |
-
"math-algebra": {"Score": 61.45954168, "Avg Rank": 32.33333333, "Min Rank": 32, "Max Rank": 33},
|
| 413 |
-
"math-probability": {"Score": 62.56195929, "Avg Rank": 32, "Min Rank": 32, "Max Rank": 32},
|
| 414 |
-
"reasoning-logical": {"Avg Rank": 32, "Min Rank": 31, "Max Rank": 33},
|
| 415 |
-
"overall": {"Avg Rank": 32, "Min Rank": 31, "Max Rank": 33}
|
| 416 |
-
}},
|
| 417 |
-
|
| 418 |
-
{"config": {
|
| 419 |
-
"model_name": "command-r-(08-2024)",
|
| 420 |
-
"organization": "Cohere",
|
| 421 |
-
"license": "CC-BY-NC-4.0",
|
| 422 |
-
"knowledge_cutoff": "2024-08"
|
| 423 |
-
},
|
| 424 |
-
"results": {
|
| 425 |
-
"math-algebra": {"Score": 61.0679475, "Avg Rank": 32.66666667, "Min Rank": 32, "Max Rank": 33},
|
| 426 |
-
"math-probability": {"Score": 66.00833826, "Avg Rank": 31, "Min Rank": 31, "Max Rank": 31},
|
| 427 |
-
"reasoning-logical": {"Avg Rank": 37.66666667, "Min Rank": 37, "Max Rank": 38},
|
| 428 |
-
"overall": {"Avg Rank": 34, "Min Rank": 31, "Max Rank": 38}
|
| 429 |
-
}},
|
| 430 |
-
|
| 431 |
-
{"config": {
|
| 432 |
-
"model_name": "gemma-1.1-7b-it",
|
| 433 |
-
"organization": "Google",
|
| 434 |
-
"license": "Gemma License",
|
| 435 |
-
"knowledge_cutoff": "2023-11"
|
| 436 |
-
},
|
| 437 |
-
"results": {
|
| 438 |
-
"math-algebra": {"Score": 60.92904194, "Avg Rank": 34.33333333, "Min Rank": 34, "Max Rank": 35},
|
| 439 |
-
"math-probability": {"Score": 62.17574935, "Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 37},
|
| 440 |
-
"reasoning-logical": {"Avg Rank": 30.33333333, "Min Rank": 28, "Max Rank": 32},
|
| 441 |
-
"overall": {"Avg Rank": 34, "Min Rank": 28, "Max Rank": 37}
|
| 442 |
-
}},
|
| 443 |
-
|
| 444 |
-
{"config": {
|
| 445 |
-
"model_name": "llama3-8b-instruct",
|
| 446 |
-
"organization": "Meta",
|
| 447 |
-
"license": "Llama 3 Community",
|
| 448 |
-
"knowledge_cutoff": "2024-01"
|
| 449 |
-
},
|
| 450 |
-
"results": {
|
| 451 |
-
"math-algebra": {"Score": 61.06411319, "Avg Rank": 35, "Min Rank": 34, "Max Rank": 36},
|
| 452 |
-
"math-probability": {"Score": 62.13077748, "Avg Rank": 34.66666667, "Min Rank": 34, "Max Rank": 35},
|
| 453 |
-
"reasoning-logical": {"Avg Rank": 22, "Min Rank": 22, "Max Rank": 22},
|
| 454 |
-
"overall": {"Avg Rank": 30, "Min Rank": 22, "Max Rank": 36}
|
| 455 |
-
}},
|
| 456 |
-
|
| 457 |
-
{"config": {
|
| 458 |
-
"model_name": "gemma-2-2b-it",
|
| 459 |
-
"organization": "Google",
|
| 460 |
-
"license": "Gemma License",
|
| 461 |
-
"knowledge_cutoff": "2023-12"
|
| 462 |
-
},
|
| 463 |
-
"results": {
|
| 464 |
-
"math-algebra": {"Score": 59.70248014, "Avg Rank": 36, "Min Rank": 35, "Max Rank": 37},
|
| 465 |
-
"math-probability": {"Score": 61.08084527, "Avg Rank": 33.66666667, "Min Rank": 33, "Max Rank": 35},
|
| 466 |
-
"reasoning-logical": {"Avg Rank": 26, "Min Rank": 26, "Max Rank": 26},
|
| 467 |
-
"overall": {"Avg Rank": 32, "Min Rank": 26, "Max Rank": 37}
|
| 468 |
-
}},
|
| 469 |
-
|
| 470 |
-
{"config": {
|
| 471 |
-
"model_name": "starling-lm-7b-alpha",
|
| 472 |
-
"organization": "Nexusflow",
|
| 473 |
-
"license": "Apache-2.0",
|
| 474 |
-
"knowledge_cutoff": "2023-12"
|
| 475 |
-
},
|
| 476 |
-
"results": {
|
| 477 |
-
"math-algebra": {"Score": 59.574329, "Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 37},
|
| 478 |
-
"math-probability": {"Score": 64.03683254, "Avg Rank": 33.66666667, "Min Rank": 33, "Max Rank": 34},
|
| 479 |
-
"reasoning-logical": {"Avg Rank": 35, "Min Rank": 35, "Max Rank": 35},
|
| 480 |
-
"overall": {"Avg Rank": 35, "Min Rank": 33, "Max Rank": 37}
|
| 481 |
-
}},
|
| 482 |
-
|
| 483 |
-
{"config": {
|
| 484 |
-
"model_name": "qwen1.5-4b-chat",
|
| 485 |
-
"organization": "Alibaba",
|
| 486 |
-
"license": "Qianwen LICENSE",
|
| 487 |
-
"knowledge_cutoff": "2024-02"
|
| 488 |
-
},
|
| 489 |
-
"results": {
|
| 490 |
-
"math-algebra": {"Score": 56.66282914, "Avg Rank": 38.33333333, "Min Rank": 38, "Max Rank": 39},
|
| 491 |
-
"math-probability": {"Score": 57.39032697, "Avg Rank": 43, "Min Rank": 43, "Max Rank": 43},
|
| 492 |
-
"reasoning-logical": {"Avg Rank": 46, "Min Rank": 46, "Max Rank": 46},
|
| 493 |
-
"overall": {"Avg Rank": 42, "Min Rank": 38, "Max Rank": 46}
|
| 494 |
-
}},
|
| 495 |
-
|
| 496 |
-
{"config": {
|
| 497 |
-
"model_name": "command-r-(04-2024)",
|
| 498 |
-
"organization": "Cohere",
|
| 499 |
-
"license": "CC-BY-NC-4.0",
|
| 500 |
-
"knowledge_cutoff": "2024-04"
|
| 501 |
-
},
|
| 502 |
-
"results": {
|
| 503 |
-
"math-algebra": {"Score": 56.19063413, "Avg Rank": 38.66666667, "Min Rank": 38, "Max Rank": 39},
|
| 504 |
-
"math-probability": {"Score": 54.37641509, "Avg Rank": 37.66666667, "Min Rank": 37, "Max Rank": 38},
|
| 505 |
-
"reasoning-logical": {"Avg Rank": 32.66666667, "Min Rank": 32, "Max Rank": 33},
|
| 506 |
-
"overall": {"Avg Rank": 36, "Min Rank": 32, "Max Rank": 39}
|
| 507 |
-
}},
|
| 508 |
-
|
| 509 |
-
{"config": {
|
| 510 |
-
"model_name": "vicuna-33b",
|
| 511 |
-
"organization": "LMSYS",
|
| 512 |
-
"license": "Non-commercial",
|
| 513 |
-
"knowledge_cutoff": "2023-12"
|
| 514 |
-
},
|
| 515 |
-
"results": {
|
| 516 |
-
"math-algebra": {"Score": 54.71037983, "Avg Rank": 40.66666667, "Min Rank": 40, "Max Rank": 42},
|
| 517 |
-
"math-probability": {"Score": 55.02214588, "Avg Rank": 41, "Min Rank": 41, "Max Rank": 41},
|
| 518 |
-
"reasoning-logical": {"Avg Rank": 41, "Min Rank": 41, "Max Rank": 41},
|
| 519 |
-
"overall": {"Avg Rank": 41, "Min Rank": 40, "Max Rank": 42}
|
| 520 |
-
}},
|
| 521 |
-
|
| 522 |
-
{"config": {
|
| 523 |
-
"model_name": "gemma-7b-it",
|
| 524 |
-
"organization": "Google",
|
| 525 |
-
"license": "Gemma License",
|
| 526 |
-
"knowledge_cutoff": "2023-12"
|
| 527 |
-
},
|
| 528 |
-
"results": {
|
| 529 |
-
"math-algebra": {"Score": 54.35817186, "Avg Rank": 40.66666667, "Min Rank": 40, "Max Rank": 41},
|
| 530 |
-
"math-probability": {"Score": 58.19573446, "Avg Rank": 42, "Min Rank": 42, "Max Rank": 42},
|
| 531 |
-
"reasoning-logical": {"Avg Rank": 39.33333333, "Min Rank": 39, "Max Rank": 40},
|
| 532 |
-
"overall": {"Avg Rank": 41, "Min Rank": 39, "Max Rank": 42}
|
| 533 |
-
}},
|
| 534 |
-
|
| 535 |
-
{"config": {
|
| 536 |
-
"model_name": "mistral-7b-instruct-2",
|
| 537 |
-
"organization": "Mistral",
|
| 538 |
-
"license": "Apache 2.0",
|
| 539 |
-
"knowledge_cutoff": "2023-12"
|
| 540 |
-
},
|
| 541 |
-
"results": {
|
| 542 |
-
"math-algebra": {"Score": 54.39240703, "Avg Rank": 41.66666667, "Min Rank": 41, "Max Rank": 42},
|
| 543 |
-
"math-probability": {"Score": 60.35257542, "Avg Rank": 39, "Min Rank": 39, "Max Rank": 39},
|
| 544 |
-
"reasoning-logical": {"Avg Rank": 36.66666667, "Min Rank": 36, "Max Rank": 37},
|
| 545 |
-
"overall": {"Avg Rank": 39, "Min Rank": 36, "Max Rank": 42}
|
| 546 |
-
}},
|
| 547 |
-
|
| 548 |
-
{"config": {
|
| 549 |
-
"model_name": "mistral-7b-instruct-1",
|
| 550 |
-
"organization": "Mistral",
|
| 551 |
-
"license": "Apache 2.0",
|
| 552 |
-
"knowledge_cutoff": "2023-12"
|
| 553 |
-
},
|
| 554 |
-
"results": {
|
| 555 |
-
"math-algebra": {"Score": 53.80157944, "Avg Rank": 43, "Min Rank": 43, "Max Rank": 43},
|
| 556 |
-
"math-probability": {"Score": 56.51960666, "Avg Rank": 40, "Min Rank": 40, "Max Rank": 40},
|
| 557 |
-
"reasoning-logical": {"Avg Rank": 45, "Min Rank": 45, "Max Rank": 45},
|
| 558 |
-
"overall": {"Avg Rank": 43, "Min Rank": 40, "Max Rank": 45}
|
| 559 |
-
}},
|
| 560 |
-
|
| 561 |
-
{"config": {
|
| 562 |
-
"model_name": "vicuna-13b",
|
| 563 |
-
"organization": "LMSYS",
|
| 564 |
-
"license": "Non-commercial",
|
| 565 |
-
"knowledge_cutoff": "2023-11"
|
| 566 |
-
},
|
| 567 |
-
"results": {
|
| 568 |
-
"math-algebra": {"Score": 53.5413765, "Avg Rank": 44, "Min Rank": 44, "Max Rank": 44},
|
| 569 |
-
"math-probability": {"Score": 53.53586693, "Avg Rank": 44, "Min Rank": 44, "Max Rank": 44},
|
| 570 |
-
"reasoning-logical": {"Avg Rank": 43.66666667, "Min Rank": 43, "Max Rank": 44},
|
| 571 |
-
"overall": {"Avg Rank": 44, "Min Rank": 43, "Max Rank": 44}
|
| 572 |
-
}},
|
| 573 |
-
|
| 574 |
-
{"config": {
|
| 575 |
-
"model_name": "zephyr-7b-beta",
|
| 576 |
-
"organization": "HuggingFace",
|
| 577 |
-
"license": "MIT",
|
| 578 |
-
"knowledge_cutoff": "2023-10"
|
| 579 |
-
},
|
| 580 |
-
"results": {
|
| 581 |
-
"math-algebra": {"Score": 52.23039742, "Avg Rank": 46, "Min Rank": 45, "Max Rank": 48},
|
| 582 |
-
"math-probability": {"Score": 51.67173535, "Avg Rank": 47.33333333, "Min Rank": 47, "Max Rank": 48},
|
| 583 |
-
"reasoning-logical": {"Avg Rank": 50, "Min Rank": 50, "Max Rank": 50},
|
| 584 |
-
"overall": {"Avg Rank": 48, "Min Rank": 45, "Max Rank": 50}
|
| 585 |
-
}},
|
| 586 |
-
|
| 587 |
-
{"config": {
|
| 588 |
-
"model_name": "gemma-1.1-2b-it",
|
| 589 |
-
"organization": "Google",
|
| 590 |
-
"license": "Gemma License",
|
| 591 |
-
"knowledge_cutoff": "2023-12"
|
| 592 |
-
},
|
| 593 |
-
"results": {
|
| 594 |
-
"math-algebra": {"Score": 52.22372428, "Avg Rank": 46, "Min Rank": 45, "Max Rank": 47},
|
| 595 |
-
"math-probability": {"Score": 51.74306688, "Avg Rank": 46.33333333, "Min Rank": 46, "Max Rank": 47},
|
| 596 |
-
"reasoning-logical": {"Avg Rank": 48, "Min Rank": 48, "Max Rank": 48},
|
| 597 |
-
"overall": {"Avg Rank": 47, "Min Rank": 45, "Max Rank": 48}
|
| 598 |
-
}},
|
| 599 |
-
|
| 600 |
-
{"config": {
|
| 601 |
-
"model_name": "llama2-7b-chat",
|
| 602 |
-
"organization": "Meta",
|
| 603 |
-
"license": "Llama 2 Community",
|
| 604 |
-
"knowledge_cutoff": "2023-10"
|
| 605 |
-
},
|
| 606 |
-
"results": {
|
| 607 |
-
"math-algebra": {"Score": 51.83025857, "Avg Rank": 46.33333333, "Min Rank": 46, "Max Rank": 47},
|
| 608 |
-
"math-probability": {"Score": 51.19585847, "Avg Rank": 47.33333333, "Min Rank": 46, "Max Rank": 48},
|
| 609 |
-
"reasoning-logical": {"Avg Rank": 42.66666667, "Min Rank": 42, "Max Rank": 43},
|
| 610 |
-
"overall": {"Avg Rank": 45, "Min Rank": 42, "Max Rank": 48}
|
| 611 |
-
}},
|
| 612 |
-
|
| 613 |
-
{"config": {
|
| 614 |
-
"model_name": "gemma-2b-it",
|
| 615 |
-
"organization": "Google",
|
| 616 |
-
"license": "Gemma License",
|
| 617 |
-
"knowledge_cutoff": "2023-11"
|
| 618 |
-
},
|
| 619 |
-
"results": {
|
| 620 |
-
"math-algebra": {"Score": 51.60281474, "Avg Rank": 47.66666667, "Min Rank": 47, "Max Rank": 48},
|
| 621 |
-
"math-probability": {"Score": 51.52250905, "Avg Rank": 50, "Min Rank": 50, "Max Rank": 50},
|
| 622 |
-
"reasoning-logical": {"Avg Rank": 51, "Min Rank": 51, "Max Rank": 51},
|
| 623 |
-
"overall": {"Avg Rank": 49, "Min Rank": 47, "Max Rank": 51}
|
| 624 |
-
}},
|
| 625 |
-
|
| 626 |
-
{"config": {
|
| 627 |
-
"model_name": "llama2-13b-chat",
|
| 628 |
-
"organization": "Meta",
|
| 629 |
-
"license": "Llama 2 Community",
|
| 630 |
-
"knowledge_cutoff": "2023-12"
|
| 631 |
-
},
|
| 632 |
-
"results": {
|
| 633 |
-
"math-algebra": {"Score": 51.21273132, "Avg Rank": 49, "Min Rank": 49, "Max Rank": 49},
|
| 634 |
-
"math-probability": {"Score": 51.72056522, "Avg Rank": 45, "Min Rank": 45, "Max Rank": 45},
|
| 635 |
-
"reasoning-logical": {"Avg Rank": 39, "Min Rank": 38, "Max Rank": 40},
|
| 636 |
-
"overall": {"Avg Rank": 44, "Min Rank": 38, "Max Rank": 49}
|
| 637 |
-
}},
|
| 638 |
-
|
| 639 |
-
{"config": {
|
| 640 |
-
"model_name": "vicuna-7b",
|
| 641 |
-
"organization": "LMSYS",
|
| 642 |
-
"license": "Non-commercial",
|
| 643 |
-
"knowledge_cutoff": "2023-11"
|
| 644 |
-
},
|
| 645 |
-
"results": {
|
| 646 |
-
"math-algebra": {"Score": 51.31450547, "Avg Rank": 50, "Min Rank": 50, "Max Rank": 50},
|
| 647 |
-
"math-probability": {"Score": 52.72504618, "Avg Rank": 49, "Min Rank": 49, "Max Rank": 49},
|
| 648 |
-
"reasoning-logical": {"Avg Rank": 47, "Min Rank": 47, "Max Rank": 47},
|
| 649 |
-
"overall": {"Avg Rank": 48, "Min Rank": 47, "Max Rank": 50}
|
| 650 |
-
}},
|
| 651 |
-
|
| 652 |
-
{"config": {
|
| 653 |
-
"model_name": "koala-13b",
|
| 654 |
-
"organization": "UC Berkeley",
|
| 655 |
-
"license": "Non-commercial",
|
| 656 |
-
"knowledge_cutoff": "2023-10"
|
| 657 |
-
},
|
| 658 |
-
"results": {
|
| 659 |
-
"math-algebra": {"Score": 50.19054677, "Avg Rank": 51, "Min Rank": 51, "Max Rank": 51},
|
| 660 |
-
"math-probability": {"Score": 50.741989, "Avg Rank": 51, "Min Rank": 51, "Max Rank": 51},
|
| 661 |
-
"reasoning-logical": {"Avg Rank": 49, "Min Rank": 49, "Max Rank": 49},
|
| 662 |
-
"overall": {"Avg Rank": 50, "Min Rank": 49, "Max Rank": 51}
|
| 663 |
-
}},
|
| 664 |
-
|
| 665 |
-
{"config": {
|
| 666 |
-
"model_name": "openassistant-pythia-12b",
|
| 667 |
-
"organization": "OpenAssistant",
|
| 668 |
-
"license": "Non-commercial",
|
| 669 |
-
"knowledge_cutoff": "2023-09"
|
| 670 |
-
},
|
| 671 |
-
"results": {
|
| 672 |
-
"math-algebra": {"Score": 50, "Avg Rank": 52, "Min Rank": 52, "Max Rank": 52},
|
| 673 |
-
"math-probability": {"Score": 50, "Avg Rank": 52, "Min Rank": 52, "Max Rank": 52},
|
| 674 |
-
"reasoning-logical": {"Avg Rank": 52, "Min Rank": 52, "Max Rank": 52},
|
| 675 |
-
"overall": {"Avg Rank": 52, "Min Rank": 52, "Max Rank": 52}
|
| 676 |
-
}}
|
| 677 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/models_2024-10-08-03:10:26.811832.jsonl
DELETED
|
@@ -1,1770 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"config": {
|
| 4 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 5 |
-
"organization": "OpenAI",
|
| 6 |
-
"license": "Proprietary",
|
| 7 |
-
"knowledge_cutoff": "2023/10"
|
| 8 |
-
},
|
| 9 |
-
"results": {
|
| 10 |
-
"OVERALL": {
|
| 11 |
-
"Score": 0.974329609,
|
| 12 |
-
"Standard Deviation": 0.005024959031
|
| 13 |
-
},
|
| 14 |
-
"Geometry": {
|
| 15 |
-
"Score": 0.976028578,
|
| 16 |
-
"Standard Deviation": 0.01507912373
|
| 17 |
-
},
|
| 18 |
-
"Algebra": {
|
| 19 |
-
"Score": 0.951199453,
|
| 20 |
-
"Standard Deviation": 0.08452452108
|
| 21 |
-
},
|
| 22 |
-
"Probability": {
|
| 23 |
-
"Score": 0.842116641,
|
| 24 |
-
"Standard Deviation": 0.006267759054
|
| 25 |
-
},
|
| 26 |
-
"Logical": {
|
| 27 |
-
"Score": 0.828490728,
|
| 28 |
-
"Standard Deviation": 0.009134213144
|
| 29 |
-
},
|
| 30 |
-
"Social": {
|
| 31 |
-
"Score": 0.815902987,
|
| 32 |
-
"Standard Deviation": 0.0196254222
|
| 33 |
-
}
|
| 34 |
-
}
|
| 35 |
-
},
|
| 36 |
-
{
|
| 37 |
-
"config": {
|
| 38 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 39 |
-
"organization": "OpenAI",
|
| 40 |
-
"license": "Proprietary",
|
| 41 |
-
"knowledge_cutoff": "2023/10"
|
| 42 |
-
},
|
| 43 |
-
"results": {
|
| 44 |
-
"OVERALL": {
|
| 45 |
-
"Score": 0.846571548,
|
| 46 |
-
"Standard Deviation": 0.03394056554
|
| 47 |
-
},
|
| 48 |
-
"Geometry": {
|
| 49 |
-
"Score": 0.99773096,
|
| 50 |
-
"Standard Deviation": 0.002835555172
|
| 51 |
-
},
|
| 52 |
-
"Algebra": {
|
| 53 |
-
"Score": 1.0,
|
| 54 |
-
"Standard Deviation": 0.0
|
| 55 |
-
},
|
| 56 |
-
"Probability": {
|
| 57 |
-
"Score": 0.78855795,
|
| 58 |
-
"Standard Deviation": 0.008188675452
|
| 59 |
-
},
|
| 60 |
-
"Logical": {
|
| 61 |
-
"Score": 0.668635768,
|
| 62 |
-
"Standard Deviation": 0.03466314094
|
| 63 |
-
},
|
| 64 |
-
"Social": {
|
| 65 |
-
"Score": 0.680417314,
|
| 66 |
-
"Standard Deviation": 0.00656867063
|
| 67 |
-
}
|
| 68 |
-
}
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"config": {
|
| 72 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 73 |
-
"organization": "OpenAI",
|
| 74 |
-
"license": "Proprietary",
|
| 75 |
-
"knowledge_cutoff": "2023/10"
|
| 76 |
-
},
|
| 77 |
-
"results": {
|
| 78 |
-
"OVERALL": {
|
| 79 |
-
"Score": 0.846334477,
|
| 80 |
-
"Standard Deviation": 0.09377911572
|
| 81 |
-
},
|
| 82 |
-
"Geometry": {
|
| 83 |
-
"Score": 0.972472377,
|
| 84 |
-
"Standard Deviation": 0.01648274205
|
| 85 |
-
},
|
| 86 |
-
"Algebra": {
|
| 87 |
-
"Score": 0.995511298,
|
| 88 |
-
"Standard Deviation": 0.004097802515
|
| 89 |
-
},
|
| 90 |
-
"Probability": {
|
| 91 |
-
"Score": 0.812149974,
|
| 92 |
-
"Standard Deviation": 0.007669585485
|
| 93 |
-
},
|
| 94 |
-
"Logical": {
|
| 95 |
-
"Score": 0.755019692,
|
| 96 |
-
"Standard Deviation": 0.008149588572
|
| 97 |
-
},
|
| 98 |
-
"Social": {
|
| 99 |
-
"Score": 0.609875087,
|
| 100 |
-
"Standard Deviation": 0.038729239
|
| 101 |
-
}
|
| 102 |
-
}
|
| 103 |
-
},
|
| 104 |
-
{
|
| 105 |
-
"config": {
|
| 106 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 107 |
-
"organization": "OpenAI",
|
| 108 |
-
"license": "Proprietary",
|
| 109 |
-
"knowledge_cutoff": "2023/12"
|
| 110 |
-
},
|
| 111 |
-
"results": {
|
| 112 |
-
"OVERALL": {
|
| 113 |
-
"Score": 0.855357972,
|
| 114 |
-
"Standard Deviation": 0.1016986368
|
| 115 |
-
},
|
| 116 |
-
"Geometry": {
|
| 117 |
-
"Score": 0.95374588,
|
| 118 |
-
"Standard Deviation": 0.03109307166
|
| 119 |
-
},
|
| 120 |
-
"Algebra": {
|
| 121 |
-
"Score": 0.930945223,
|
| 122 |
-
"Standard Deviation": 0.06705136813
|
| 123 |
-
},
|
| 124 |
-
"Probability": {
|
| 125 |
-
"Score": 0.750705448,
|
| 126 |
-
"Standard Deviation": 0.05944483103
|
| 127 |
-
},
|
| 128 |
-
"Logical": {
|
| 129 |
-
"Score": 0.77906699,
|
| 130 |
-
"Standard Deviation": 0.007406734161
|
| 131 |
-
},
|
| 132 |
-
"Social": {
|
| 133 |
-
"Score": 0.715935163,
|
| 134 |
-
"Standard Deviation": 0.1209141409
|
| 135 |
-
}
|
| 136 |
-
}
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"config": {
|
| 140 |
-
"model_name": "gemini-1.5-pro-001",
|
| 141 |
-
"organization": "Google",
|
| 142 |
-
"license": "Proprietary",
|
| 143 |
-
"knowledge_cutoff": "2024-01"
|
| 144 |
-
},
|
| 145 |
-
"results": {
|
| 146 |
-
"OVERALL": {
|
| 147 |
-
"Score": 0.797187842,
|
| 148 |
-
"Standard Deviation": 0.0272375249
|
| 149 |
-
},
|
| 150 |
-
"Geometry": {
|
| 151 |
-
"Score": 0.9947169,
|
| 152 |
-
"Standard Deviation": 0.009150597621
|
| 153 |
-
},
|
| 154 |
-
"Algebra": {
|
| 155 |
-
"Score": 0.857464301,
|
| 156 |
-
"Standard Deviation": 0.05014285338
|
| 157 |
-
},
|
| 158 |
-
"Probability": {
|
| 159 |
-
"Score": 0.651781767,
|
| 160 |
-
"Standard Deviation": 0.04156998547
|
| 161 |
-
},
|
| 162 |
-
"Logical": {
|
| 163 |
-
"Score": 0.739745471,
|
| 164 |
-
"Standard Deviation": 0.01631532019
|
| 165 |
-
},
|
| 166 |
-
"Social": {
|
| 167 |
-
"Score": 0.649601885,
|
| 168 |
-
"Standard Deviation": 0.104854889
|
| 169 |
-
}
|
| 170 |
-
}
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"config": {
|
| 174 |
-
"model_name": "qwen2-72b-instruct",
|
| 175 |
-
"organization": "Alibaba",
|
| 176 |
-
"license": "Qianwen LICENSE",
|
| 177 |
-
"knowledge_cutoff": "2024-02"
|
| 178 |
-
},
|
| 179 |
-
"results": {
|
| 180 |
-
"OVERALL": {
|
| 181 |
-
"Score": 0.737918558,
|
| 182 |
-
"Standard Deviation": 0.09069077339
|
| 183 |
-
},
|
| 184 |
-
"Geometry": {
|
| 185 |
-
"Score": 0.796870305,
|
| 186 |
-
"Standard Deviation": 0.0509025346
|
| 187 |
-
},
|
| 188 |
-
"Algebra": {
|
| 189 |
-
"Score": 0.836194231,
|
| 190 |
-
"Standard Deviation": 0.04517093028
|
| 191 |
-
},
|
| 192 |
-
"Probability": {
|
| 193 |
-
"Score": 0.788068004,
|
| 194 |
-
"Standard Deviation": 0.007288989044
|
| 195 |
-
},
|
| 196 |
-
"Logical": {
|
| 197 |
-
"Score": 0.619300904,
|
| 198 |
-
"Standard Deviation": 0.06377931612
|
| 199 |
-
},
|
| 200 |
-
"Social": {
|
| 201 |
-
"Score": 0.652578786,
|
| 202 |
-
"Standard Deviation": 0.04259293171
|
| 203 |
-
}
|
| 204 |
-
}
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"config": {
|
| 208 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 209 |
-
"organization": "OpenAI",
|
| 210 |
-
"license": "Proprietary",
|
| 211 |
-
"knowledge_cutoff": "2024-07"
|
| 212 |
-
},
|
| 213 |
-
"results": {
|
| 214 |
-
"OVERALL": {
|
| 215 |
-
"Score": 0.847694133,
|
| 216 |
-
"Standard Deviation": 0.02164304402
|
| 217 |
-
},
|
| 218 |
-
"Geometry": {
|
| 219 |
-
"Score": 0.946650435,
|
| 220 |
-
"Standard Deviation": 0.01831236482
|
| 221 |
-
},
|
| 222 |
-
"Algebra": {
|
| 223 |
-
"Score": 0.796243022,
|
| 224 |
-
"Standard Deviation": 0.05537539202
|
| 225 |
-
},
|
| 226 |
-
"Probability": {
|
| 227 |
-
"Score": 0.798402685,
|
| 228 |
-
"Standard Deviation": 0.009404491967
|
| 229 |
-
},
|
| 230 |
-
"Logical": {
|
| 231 |
-
"Score": 0.727009735,
|
| 232 |
-
"Standard Deviation": 0.02628110141
|
| 233 |
-
},
|
| 234 |
-
"Social": {
|
| 235 |
-
"Score": 0.691949855,
|
| 236 |
-
"Standard Deviation": 0.02072934333
|
| 237 |
-
}
|
| 238 |
-
}
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"config": {
|
| 242 |
-
"model_name": "claude-3.5-sonnet",
|
| 243 |
-
"organization": "Anthropic",
|
| 244 |
-
"license": "Proprietary",
|
| 245 |
-
"knowledge_cutoff": "2024-03"
|
| 246 |
-
},
|
| 247 |
-
"results": {
|
| 248 |
-
"OVERALL": {
|
| 249 |
-
"Score": 0.839004422,
|
| 250 |
-
"Standard Deviation": 0.1461079564
|
| 251 |
-
},
|
| 252 |
-
"Geometry": {
|
| 253 |
-
"Score": 0.95316419,
|
| 254 |
-
"Standard Deviation": 0.02081192856
|
| 255 |
-
},
|
| 256 |
-
"Algebra": {
|
| 257 |
-
"Score": 0.759789952,
|
| 258 |
-
"Standard Deviation": 0.02611765096
|
| 259 |
-
},
|
| 260 |
-
"Probability": {
|
| 261 |
-
"Score": 0.707730127,
|
| 262 |
-
"Standard Deviation": 0.0394436664
|
| 263 |
-
},
|
| 264 |
-
"Logical": {
|
| 265 |
-
"Score": 0.77342666,
|
| 266 |
-
"Standard Deviation": 0.002892426458
|
| 267 |
-
},
|
| 268 |
-
"Social": {
|
| 269 |
-
"Score": 0.790002247,
|
| 270 |
-
"Standard Deviation": 0.1007410022
|
| 271 |
-
}
|
| 272 |
-
}
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"config": {
|
| 276 |
-
"model_name": "o1-mini",
|
| 277 |
-
"organization": "OpenAI",
|
| 278 |
-
"license": "Proprietary",
|
| 279 |
-
"knowledge_cutoff": "2024-01"
|
| 280 |
-
},
|
| 281 |
-
"results": {
|
| 282 |
-
"OVERALL": {
|
| 283 |
-
"Score": 1.0,
|
| 284 |
-
"Standard Deviation": 0.0
|
| 285 |
-
},
|
| 286 |
-
"Geometry": {
|
| 287 |
-
"Score": "N/A",
|
| 288 |
-
"Standard Deviation": "N/A"
|
| 289 |
-
},
|
| 290 |
-
"Algebra": {
|
| 291 |
-
"Score": "N/A",
|
| 292 |
-
"Standard Deviation": "N/A"
|
| 293 |
-
},
|
| 294 |
-
"Probability": {
|
| 295 |
-
"Score": 1.0,
|
| 296 |
-
"Standard Deviation": 0.0
|
| 297 |
-
},
|
| 298 |
-
"Logical": {
|
| 299 |
-
"Score": 1.0,
|
| 300 |
-
"Standard Deviation": 0.0
|
| 301 |
-
},
|
| 302 |
-
"Social": {
|
| 303 |
-
"Score": 0.993974241,
|
| 304 |
-
"Standard Deviation": 0.001996882328
|
| 305 |
-
}
|
| 306 |
-
}
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"config": {
|
| 310 |
-
"model_name": "o1-preview",
|
| 311 |
-
"organization": "OpenAI",
|
| 312 |
-
"license": "Proprietary",
|
| 313 |
-
"knowledge_cutoff": "2024-01"
|
| 314 |
-
},
|
| 315 |
-
"results": {
|
| 316 |
-
"OVERALL": {
|
| 317 |
-
"Score": 0.945884589,
|
| 318 |
-
"Standard Deviation": 0.01059250762
|
| 319 |
-
},
|
| 320 |
-
"Geometry": {
|
| 321 |
-
"Score": "N/A",
|
| 322 |
-
"Standard Deviation": "N/A"
|
| 323 |
-
},
|
| 324 |
-
"Algebra": {
|
| 325 |
-
"Score": "N/A",
|
| 326 |
-
"Standard Deviation": "N/A"
|
| 327 |
-
},
|
| 328 |
-
"Probability": {
|
| 329 |
-
"Score": 0.964666392,
|
| 330 |
-
"Standard Deviation": 0.003139983398
|
| 331 |
-
},
|
| 332 |
-
"Logical": {
|
| 333 |
-
"Score": 0.987950057,
|
| 334 |
-
"Standard Deviation": 0.004881220327
|
| 335 |
-
},
|
| 336 |
-
"Social": {
|
| 337 |
-
"Score": 1.0,
|
| 338 |
-
"Standard Deviation": 0.0
|
| 339 |
-
}
|
| 340 |
-
}
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"config": {
|
| 344 |
-
"model_name": "gemini-1.5-flash-001",
|
| 345 |
-
"organization": "Google",
|
| 346 |
-
"license": "Proprietary",
|
| 347 |
-
"knowledge_cutoff": "2024-02"
|
| 348 |
-
},
|
| 349 |
-
"results": {
|
| 350 |
-
"OVERALL": {
|
| 351 |
-
"Score": 0.726493401,
|
| 352 |
-
"Standard Deviation": 0.01113913725
|
| 353 |
-
},
|
| 354 |
-
"Geometry": {
|
| 355 |
-
"Score": 0.804144103,
|
| 356 |
-
"Standard Deviation": 0.1327142178
|
| 357 |
-
},
|
| 358 |
-
"Algebra": {
|
| 359 |
-
"Score": 0.731776765,
|
| 360 |
-
"Standard Deviation": 0.02594657111
|
| 361 |
-
},
|
| 362 |
-
"Probability": {
|
| 363 |
-
"Score": 0.614461891,
|
| 364 |
-
"Standard Deviation": 0.04690131826
|
| 365 |
-
},
|
| 366 |
-
"Logical": {
|
| 367 |
-
"Score": 0.630805991,
|
| 368 |
-
"Standard Deviation": 0.04871350612
|
| 369 |
-
},
|
| 370 |
-
"Social": {
|
| 371 |
-
"Score": 0.555933822,
|
| 372 |
-
"Standard Deviation": 0.1029934524
|
| 373 |
-
}
|
| 374 |
-
}
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"config": {
|
| 378 |
-
"model_name": "gpt4-1106",
|
| 379 |
-
"organization": "OpenAI",
|
| 380 |
-
"license": "Proprietary",
|
| 381 |
-
"knowledge_cutoff": "2024-04"
|
| 382 |
-
},
|
| 383 |
-
"results": {
|
| 384 |
-
"OVERALL": {
|
| 385 |
-
"Score": 0.816347784,
|
| 386 |
-
"Standard Deviation": 0.1566815755
|
| 387 |
-
},
|
| 388 |
-
"Geometry": {
|
| 389 |
-
"Score": 0.71843088,
|
| 390 |
-
"Standard Deviation": 0.04778038294
|
| 391 |
-
},
|
| 392 |
-
"Algebra": {
|
| 393 |
-
"Score": 0.712910417,
|
| 394 |
-
"Standard Deviation": 0.02581828898
|
| 395 |
-
},
|
| 396 |
-
"Probability": {
|
| 397 |
-
"Score": 0.623947619,
|
| 398 |
-
"Standard Deviation": 0.03502982933
|
| 399 |
-
},
|
| 400 |
-
"Logical": {
|
| 401 |
-
"Score": 0.637482274,
|
| 402 |
-
"Standard Deviation": 0.04158809888
|
| 403 |
-
},
|
| 404 |
-
"Social": {
|
| 405 |
-
"Score": 0.450609816,
|
| 406 |
-
"Standard Deviation": 0.05208655446
|
| 407 |
-
}
|
| 408 |
-
}
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"config": {
|
| 412 |
-
"model_name": "gemma-2-27b-it",
|
| 413 |
-
"organization": "Google",
|
| 414 |
-
"license": "Gemma License",
|
| 415 |
-
"knowledge_cutoff": "2024-03"
|
| 416 |
-
},
|
| 417 |
-
"results": {
|
| 418 |
-
"OVERALL": {
|
| 419 |
-
"Score": 0.624169623,
|
| 420 |
-
"Standard Deviation": 0.1048365121
|
| 421 |
-
},
|
| 422 |
-
"Geometry": {
|
| 423 |
-
"Score": 0.60112744,
|
| 424 |
-
"Standard Deviation": 0.0469109952
|
| 425 |
-
},
|
| 426 |
-
"Algebra": {
|
| 427 |
-
"Score": 0.687955914,
|
| 428 |
-
"Standard Deviation": 0.01959958192
|
| 429 |
-
},
|
| 430 |
-
"Probability": {
|
| 431 |
-
"Score": 0.589524771,
|
| 432 |
-
"Standard Deviation": 0.03112689325
|
| 433 |
-
},
|
| 434 |
-
"Logical": {
|
| 435 |
-
"Score": 0.614978944,
|
| 436 |
-
"Standard Deviation": 0.05710657859
|
| 437 |
-
},
|
| 438 |
-
"Social": {
|
| 439 |
-
"Score": 0.487844257,
|
| 440 |
-
"Standard Deviation": 0.05857760809
|
| 441 |
-
}
|
| 442 |
-
}
|
| 443 |
-
},
|
| 444 |
-
{
|
| 445 |
-
"config": {
|
| 446 |
-
"model_name": "claude-3-opus",
|
| 447 |
-
"organization": "Anthropic",
|
| 448 |
-
"license": "Proprietary",
|
| 449 |
-
"knowledge_cutoff": "2024-01"
|
| 450 |
-
},
|
| 451 |
-
"results": {
|
| 452 |
-
"OVERALL": {
|
| 453 |
-
"Score": 0.650636271,
|
| 454 |
-
"Standard Deviation": 0.1197773541
|
| 455 |
-
},
|
| 456 |
-
"Geometry": {
|
| 457 |
-
"Score": 0.7215743,
|
| 458 |
-
"Standard Deviation": 0.04712598358
|
| 459 |
-
},
|
| 460 |
-
"Algebra": {
|
| 461 |
-
"Score": 0.68777327,
|
| 462 |
-
"Standard Deviation": 0.02382683713
|
| 463 |
-
},
|
| 464 |
-
"Probability": {
|
| 465 |
-
"Score": 0.626471421,
|
| 466 |
-
"Standard Deviation": 0.02911817976
|
| 467 |
-
},
|
| 468 |
-
"Logical": {
|
| 469 |
-
"Score": 0.692346381,
|
| 470 |
-
"Standard Deviation": 0.03617185198
|
| 471 |
-
},
|
| 472 |
-
"Social": {
|
| 473 |
-
"Score": 0.663410854,
|
| 474 |
-
"Standard Deviation": 0.09540220876
|
| 475 |
-
}
|
| 476 |
-
}
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"config": {
|
| 480 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 481 |
-
"organization": "Google",
|
| 482 |
-
"license": "Gemma License",
|
| 483 |
-
"knowledge_cutoff": "2024-02"
|
| 484 |
-
},
|
| 485 |
-
"results": {
|
| 486 |
-
"OVERALL": {
|
| 487 |
-
"Score": "N/A",
|
| 488 |
-
"Standard Deviation": "N/A"
|
| 489 |
-
},
|
| 490 |
-
"Geometry": {
|
| 491 |
-
"Score": 0.582787508,
|
| 492 |
-
"Standard Deviation": 0.03965204074
|
| 493 |
-
},
|
| 494 |
-
"Algebra": {
|
| 495 |
-
"Score": 0.658648133,
|
| 496 |
-
"Standard Deviation": 0.02565919856
|
| 497 |
-
},
|
| 498 |
-
"Probability": {
|
| 499 |
-
"Score": 0.547861265,
|
| 500 |
-
"Standard Deviation": 0.02885209131
|
| 501 |
-
},
|
| 502 |
-
"Logical": {
|
| 503 |
-
"Score": 0.540720893,
|
| 504 |
-
"Standard Deviation": 0.01970134508
|
| 505 |
-
},
|
| 506 |
-
"Social": {
|
| 507 |
-
"Score": 0.635266187,
|
| 508 |
-
"Standard Deviation": 0.03620021751
|
| 509 |
-
}
|
| 510 |
-
}
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"config": {
|
| 514 |
-
"model_name": "qwen1.5-72b-chat",
|
| 515 |
-
"organization": "Alibaba",
|
| 516 |
-
"license": "Qianwen LICENSE",
|
| 517 |
-
"knowledge_cutoff": "2024-03"
|
| 518 |
-
},
|
| 519 |
-
"results": {
|
| 520 |
-
"OVERALL": {
|
| 521 |
-
"Score": 0.519549796,
|
| 522 |
-
"Standard Deviation": 0.00903634343
|
| 523 |
-
},
|
| 524 |
-
"Geometry": {
|
| 525 |
-
"Score": 0.543139301,
|
| 526 |
-
"Standard Deviation": 0.03425202326
|
| 527 |
-
},
|
| 528 |
-
"Algebra": {
|
| 529 |
-
"Score": 0.635228729,
|
| 530 |
-
"Standard Deviation": 0.01944043425
|
| 531 |
-
},
|
| 532 |
-
"Probability": {
|
| 533 |
-
"Score": 0.486948658,
|
| 534 |
-
"Standard Deviation": 0.06064655315
|
| 535 |
-
},
|
| 536 |
-
"Logical": {
|
| 537 |
-
"Score": 0.284069394,
|
| 538 |
-
"Standard Deviation": 0.02686608506
|
| 539 |
-
},
|
| 540 |
-
"Social": {
|
| 541 |
-
"Score": 0.415007627,
|
| 542 |
-
"Standard Deviation": 0.03920053159
|
| 543 |
-
}
|
| 544 |
-
}
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"config": {
|
| 548 |
-
"model_name": "qwen1.5-32b-chat",
|
| 549 |
-
"organization": "Alibaba",
|
| 550 |
-
"license": "Qianwen LICENSE",
|
| 551 |
-
"knowledge_cutoff": "2024-03"
|
| 552 |
-
},
|
| 553 |
-
"results": {
|
| 554 |
-
"OVERALL": {
|
| 555 |
-
"Score": 0.393789407,
|
| 556 |
-
"Standard Deviation": 0.05413770095
|
| 557 |
-
},
|
| 558 |
-
"Geometry": {
|
| 559 |
-
"Score": 0.51086835,
|
| 560 |
-
"Standard Deviation": 0.04052471998
|
| 561 |
-
},
|
| 562 |
-
"Algebra": {
|
| 563 |
-
"Score": 0.609003168,
|
| 564 |
-
"Standard Deviation": 0.04874143541
|
| 565 |
-
},
|
| 566 |
-
"Probability": {
|
| 567 |
-
"Score": 0.476300002,
|
| 568 |
-
"Standard Deviation": 0.05322403912
|
| 569 |
-
},
|
| 570 |
-
"Logical": {
|
| 571 |
-
"Score": 0.331781014,
|
| 572 |
-
"Standard Deviation": 0.004938997686
|
| 573 |
-
},
|
| 574 |
-
"Social": {
|
| 575 |
-
"Score": 0.380987334,
|
| 576 |
-
"Standard Deviation": 0.03762251776
|
| 577 |
-
}
|
| 578 |
-
}
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"config": {
|
| 582 |
-
"model_name": "google-gemma-2-9b-it",
|
| 583 |
-
"organization": "Google",
|
| 584 |
-
"license": "Proprietary",
|
| 585 |
-
"knowledge_cutoff": "2024-01"
|
| 586 |
-
},
|
| 587 |
-
"results": {
|
| 588 |
-
"OVERALL": {
|
| 589 |
-
"Score": 0.489663449,
|
| 590 |
-
"Standard Deviation": 0.002595702019
|
| 591 |
-
},
|
| 592 |
-
"Geometry": {
|
| 593 |
-
"Score": 0.575371308,
|
| 594 |
-
"Standard Deviation": 0.03556220251
|
| 595 |
-
},
|
| 596 |
-
"Algebra": {
|
| 597 |
-
"Score": 0.597045661,
|
| 598 |
-
"Standard Deviation": 0.0313828123
|
| 599 |
-
},
|
| 600 |
-
"Probability": {
|
| 601 |
-
"Score": 0.589221807,
|
| 602 |
-
"Standard Deviation": 0.03110811656
|
| 603 |
-
},
|
| 604 |
-
"Logical": {
|
| 605 |
-
"Score": 0.587579897,
|
| 606 |
-
"Standard Deviation": 0.05512716783
|
| 607 |
-
},
|
| 608 |
-
"Social": {
|
| 609 |
-
"Score": 0.768337958,
|
| 610 |
-
"Standard Deviation": 0.04078610476
|
| 611 |
-
}
|
| 612 |
-
}
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"config": {
|
| 616 |
-
"model_name": "yi-1.5-34b-chat",
|
| 617 |
-
"organization": "01 AI",
|
| 618 |
-
"license": "Proprietary",
|
| 619 |
-
"knowledge_cutoff": "2024-01"
|
| 620 |
-
},
|
| 621 |
-
"results": {
|
| 622 |
-
"OVERALL": {
|
| 623 |
-
"Score": 0.607812897,
|
| 624 |
-
"Standard Deviation": 0.1440881293
|
| 625 |
-
},
|
| 626 |
-
"Geometry": {
|
| 627 |
-
"Score": 0.566666724,
|
| 628 |
-
"Standard Deviation": 0.04001381658
|
| 629 |
-
},
|
| 630 |
-
"Algebra": {
|
| 631 |
-
"Score": 0.590997292,
|
| 632 |
-
"Standard Deviation": 0.03594087315
|
| 633 |
-
},
|
| 634 |
-
"Probability": {
|
| 635 |
-
"Score": 0.589524589,
|
| 636 |
-
"Standard Deviation": 0.03112618772
|
| 637 |
-
},
|
| 638 |
-
"Logical": {
|
| 639 |
-
"Score": 0.574105508,
|
| 640 |
-
"Standard Deviation": 0.03441737941
|
| 641 |
-
},
|
| 642 |
-
"Social": {
|
| 643 |
-
"Score": 0.516980832,
|
| 644 |
-
"Standard Deviation": 0.03369347985
|
| 645 |
-
}
|
| 646 |
-
}
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"config": {
|
| 650 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 651 |
-
"organization": "Meta",
|
| 652 |
-
"license": "Llama 3.1 Community",
|
| 653 |
-
"knowledge_cutoff": "2024-02"
|
| 654 |
-
},
|
| 655 |
-
"results": {
|
| 656 |
-
"OVERALL": {
|
| 657 |
-
"Score": 0.505936324,
|
| 658 |
-
"Standard Deviation": 0.05286756493
|
| 659 |
-
},
|
| 660 |
-
"Geometry": {
|
| 661 |
-
"Score": 0.522442162,
|
| 662 |
-
"Standard Deviation": 0.03908236317
|
| 663 |
-
},
|
| 664 |
-
"Algebra": {
|
| 665 |
-
"Score": 0.582702645,
|
| 666 |
-
"Standard Deviation": 0.05002277711
|
| 667 |
-
},
|
| 668 |
-
"Probability": {
|
| 669 |
-
"Score": 0.495001149,
|
| 670 |
-
"Standard Deviation": 0.05244587037
|
| 671 |
-
},
|
| 672 |
-
"Logical": {
|
| 673 |
-
"Score": 0.443030561,
|
| 674 |
-
"Standard Deviation": 0.01343820628
|
| 675 |
-
},
|
| 676 |
-
"Social": {
|
| 677 |
-
"Score": 0.329195941,
|
| 678 |
-
"Standard Deviation": 0.03925019528
|
| 679 |
-
}
|
| 680 |
-
}
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"config": {
|
| 684 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 685 |
-
"organization": "OpenAI",
|
| 686 |
-
"license": "Proprietary",
|
| 687 |
-
"knowledge_cutoff": "2023-12"
|
| 688 |
-
},
|
| 689 |
-
"results": {
|
| 690 |
-
"OVERALL": {
|
| 691 |
-
"Score": 0.313398088,
|
| 692 |
-
"Standard Deviation": 0.09322528606
|
| 693 |
-
},
|
| 694 |
-
"Geometry": {
|
| 695 |
-
"Score": 0.678714519,
|
| 696 |
-
"Standard Deviation": 0.05926546762
|
| 697 |
-
},
|
| 698 |
-
"Algebra": {
|
| 699 |
-
"Score": 0.569296173,
|
| 700 |
-
"Standard Deviation": 0.05277281097
|
| 701 |
-
},
|
| 702 |
-
"Probability": {
|
| 703 |
-
"Score": 0.448460767,
|
| 704 |
-
"Standard Deviation": 0.05768095196
|
| 705 |
-
},
|
| 706 |
-
"Logical": {
|
| 707 |
-
"Score": 0.148521348,
|
| 708 |
-
"Standard Deviation": 0.04033712907
|
| 709 |
-
},
|
| 710 |
-
"Social": {
|
| 711 |
-
"Score": 0.235071541,
|
| 712 |
-
"Standard Deviation": 0.02632892457
|
| 713 |
-
}
|
| 714 |
-
}
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"config": {
|
| 718 |
-
"model_name": "llama-3-70b-instruct",
|
| 719 |
-
"organization": "Meta",
|
| 720 |
-
"license": "Llama 3 Community",
|
| 721 |
-
"knowledge_cutoff": "2024-03"
|
| 722 |
-
},
|
| 723 |
-
"results": {
|
| 724 |
-
"OVERALL": {
|
| 725 |
-
"Score": 0.456689885,
|
| 726 |
-
"Standard Deviation": 0.01385989995
|
| 727 |
-
},
|
| 728 |
-
"Geometry": {
|
| 729 |
-
"Score": 0.516865529,
|
| 730 |
-
"Standard Deviation": 0.03858112564
|
| 731 |
-
},
|
| 732 |
-
"Algebra": {
|
| 733 |
-
"Score": 0.566756531,
|
| 734 |
-
"Standard Deviation": 0.03369826926
|
| 735 |
-
},
|
| 736 |
-
"Probability": {
|
| 737 |
-
"Score": 0.513857306,
|
| 738 |
-
"Standard Deviation": 0.05453699062
|
| 739 |
-
},
|
| 740 |
-
"Logical": {
|
| 741 |
-
"Score": 0.713796415,
|
| 742 |
-
"Standard Deviation": 0.02031215107
|
| 743 |
-
},
|
| 744 |
-
"Social": {
|
| 745 |
-
"Score": 0.45872939,
|
| 746 |
-
"Standard Deviation": 0.05347039576
|
| 747 |
-
}
|
| 748 |
-
}
|
| 749 |
-
},
|
| 750 |
-
{
|
| 751 |
-
"config": {
|
| 752 |
-
"model_name": "claude-3-sonnet",
|
| 753 |
-
"organization": "Anthropic",
|
| 754 |
-
"license": "Proprietary",
|
| 755 |
-
"knowledge_cutoff": "2024-02"
|
| 756 |
-
},
|
| 757 |
-
"results": {
|
| 758 |
-
"OVERALL": {
|
| 759 |
-
"Score": 0.520010833,
|
| 760 |
-
"Standard Deviation": 0.005030563799
|
| 761 |
-
},
|
| 762 |
-
"Geometry": {
|
| 763 |
-
"Score": 0.675613638,
|
| 764 |
-
"Standard Deviation": 0.05275594408
|
| 765 |
-
},
|
| 766 |
-
"Algebra": {
|
| 767 |
-
"Score": 0.552025728,
|
| 768 |
-
"Standard Deviation": 0.04122192409
|
| 769 |
-
},
|
| 770 |
-
"Probability": {
|
| 771 |
-
"Score": 0.516192848,
|
| 772 |
-
"Standard Deviation": 0.04152293217
|
| 773 |
-
},
|
| 774 |
-
"Logical": {
|
| 775 |
-
"Score": 0.588545747,
|
| 776 |
-
"Standard Deviation": 0.06068211943
|
| 777 |
-
},
|
| 778 |
-
"Social": {
|
| 779 |
-
"Score": 0.570437582,
|
| 780 |
-
"Standard Deviation": 0.08607040862
|
| 781 |
-
}
|
| 782 |
-
}
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"config": {
|
| 786 |
-
"model_name": "qwen1.5-14b-chat",
|
| 787 |
-
"organization": "Alibaba",
|
| 788 |
-
"license": "Qianwen LICENSE",
|
| 789 |
-
"knowledge_cutoff": "2024-01"
|
| 790 |
-
},
|
| 791 |
-
"results": {
|
| 792 |
-
"OVERALL": {
|
| 793 |
-
"Score": 0.415328996,
|
| 794 |
-
"Standard Deviation": 0.0743938717
|
| 795 |
-
},
|
| 796 |
-
"Geometry": {
|
| 797 |
-
"Score": 0.452504016,
|
| 798 |
-
"Standard Deviation": 0.04225594393
|
| 799 |
-
},
|
| 800 |
-
"Algebra": {
|
| 801 |
-
"Score": 0.538655725,
|
| 802 |
-
"Standard Deviation": 0.03721542594
|
| 803 |
-
},
|
| 804 |
-
"Probability": {
|
| 805 |
-
"Score": 0.397185975,
|
| 806 |
-
"Standard Deviation": 0.05607695946
|
| 807 |
-
},
|
| 808 |
-
"Logical": {
|
| 809 |
-
"Score": 0.264573129,
|
| 810 |
-
"Standard Deviation": 0.03936133174
|
| 811 |
-
},
|
| 812 |
-
"Social": {
|
| 813 |
-
"Score": 0.287370142,
|
| 814 |
-
"Standard Deviation": 0.04264085315
|
| 815 |
-
}
|
| 816 |
-
}
|
| 817 |
-
},
|
| 818 |
-
{
|
| 819 |
-
"config": {
|
| 820 |
-
"model_name": "claude-3-haiku",
|
| 821 |
-
"organization": "Anthropic",
|
| 822 |
-
"license": "Proprietary",
|
| 823 |
-
"knowledge_cutoff": "2024-01"
|
| 824 |
-
},
|
| 825 |
-
"results": {
|
| 826 |
-
"OVERALL": {
|
| 827 |
-
"Score": 0.453901163,
|
| 828 |
-
"Standard Deviation": 0.003604084261
|
| 829 |
-
},
|
| 830 |
-
"Geometry": {
|
| 831 |
-
"Score": 0.607993912,
|
| 832 |
-
"Standard Deviation": 0.05793460748
|
| 833 |
-
},
|
| 834 |
-
"Algebra": {
|
| 835 |
-
"Score": 0.520054055,
|
| 836 |
-
"Standard Deviation": 0.03333544511
|
| 837 |
-
},
|
| 838 |
-
"Probability": {
|
| 839 |
-
"Score": 0.474460688,
|
| 840 |
-
"Standard Deviation": 0.0446501933
|
| 841 |
-
},
|
| 842 |
-
"Logical": {
|
| 843 |
-
"Score": 0.512815976,
|
| 844 |
-
"Standard Deviation": 0.0163264281
|
| 845 |
-
},
|
| 846 |
-
"Social": {
|
| 847 |
-
"Score": 0.551083976,
|
| 848 |
-
"Standard Deviation": 0.05374722539
|
| 849 |
-
}
|
| 850 |
-
}
|
| 851 |
-
},
|
| 852 |
-
{
|
| 853 |
-
"config": {
|
| 854 |
-
"model_name": "claude-2.1",
|
| 855 |
-
"organization": "Anthropic",
|
| 856 |
-
"license": "Proprietary",
|
| 857 |
-
"knowledge_cutoff": "2023-12"
|
| 858 |
-
},
|
| 859 |
-
"results": {
|
| 860 |
-
"OVERALL": {
|
| 861 |
-
"Score": 0.35814708,
|
| 862 |
-
"Standard Deviation": 0.09168134168
|
| 863 |
-
},
|
| 864 |
-
"Geometry": {
|
| 865 |
-
"Score": 0.62752395,
|
| 866 |
-
"Standard Deviation": 0.07232659398
|
| 867 |
-
},
|
| 868 |
-
"Algebra": {
|
| 869 |
-
"Score": 0.508849609,
|
| 870 |
-
"Standard Deviation": 0.0346897465
|
| 871 |
-
},
|
| 872 |
-
"Probability": {
|
| 873 |
-
"Score": 0.41477086,
|
| 874 |
-
"Standard Deviation": 0.05964060239
|
| 875 |
-
},
|
| 876 |
-
"Logical": {
|
| 877 |
-
"Score": 0.482923674,
|
| 878 |
-
"Standard Deviation": 0.01989147048
|
| 879 |
-
},
|
| 880 |
-
"Social": {
|
| 881 |
-
"Score": 0.333804568,
|
| 882 |
-
"Standard Deviation": 0.03775548253
|
| 883 |
-
}
|
| 884 |
-
}
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"config": {
|
| 888 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 889 |
-
"organization": "Mistral",
|
| 890 |
-
"license": "Apache 2.0",
|
| 891 |
-
"knowledge_cutoff": "2023-12"
|
| 892 |
-
},
|
| 893 |
-
"results": {
|
| 894 |
-
"OVERALL": {
|
| 895 |
-
"Score": 0.382659161,
|
| 896 |
-
"Standard Deviation": 0.07594496929
|
| 897 |
-
},
|
| 898 |
-
"Geometry": {
|
| 899 |
-
"Score": 0.432216097,
|
| 900 |
-
"Standard Deviation": 0.04747949254
|
| 901 |
-
},
|
| 902 |
-
"Algebra": {
|
| 903 |
-
"Score": 0.478314888,
|
| 904 |
-
"Standard Deviation": 0.01998797419
|
| 905 |
-
},
|
| 906 |
-
"Probability": {
|
| 907 |
-
"Score": 0.427144725,
|
| 908 |
-
"Standard Deviation": 0.0590923329
|
| 909 |
-
},
|
| 910 |
-
"Logical": {
|
| 911 |
-
"Score": 0.340041983,
|
| 912 |
-
"Standard Deviation": 0.008397574592
|
| 913 |
-
},
|
| 914 |
-
"Social": {
|
| 915 |
-
"Score": 0.251949622,
|
| 916 |
-
"Standard Deviation": 0.03346674405
|
| 917 |
-
}
|
| 918 |
-
}
|
| 919 |
-
},
|
| 920 |
-
{
|
| 921 |
-
"config": {
|
| 922 |
-
"model_name": "claude-2.0",
|
| 923 |
-
"organization": "Anthropic",
|
| 924 |
-
"license": "Proprietary",
|
| 925 |
-
"knowledge_cutoff": "2023-10"
|
| 926 |
-
},
|
| 927 |
-
"results": {
|
| 928 |
-
"OVERALL": {
|
| 929 |
-
"Score": 0.322718057,
|
| 930 |
-
"Standard Deviation": 0.08369883584
|
| 931 |
-
},
|
| 932 |
-
"Geometry": {
|
| 933 |
-
"Score": 0.604141967,
|
| 934 |
-
"Standard Deviation": 0.05116441826
|
| 935 |
-
},
|
| 936 |
-
"Algebra": {
|
| 937 |
-
"Score": 0.474350734,
|
| 938 |
-
"Standard Deviation": 0.01510393066
|
| 939 |
-
},
|
| 940 |
-
"Probability": {
|
| 941 |
-
"Score": 0.437950412,
|
| 942 |
-
"Standard Deviation": 0.05985594317
|
| 943 |
-
},
|
| 944 |
-
"Logical": {
|
| 945 |
-
"Score": 0.445620646,
|
| 946 |
-
"Standard Deviation": 0.01812614805
|
| 947 |
-
},
|
| 948 |
-
"Social": {
|
| 949 |
-
"Score": 0.469422836,
|
| 950 |
-
"Standard Deviation": 0.05999901796
|
| 951 |
-
}
|
| 952 |
-
}
|
| 953 |
-
},
|
| 954 |
-
{
|
| 955 |
-
"config": {
|
| 956 |
-
"model_name": "starling-lm-7b-beta",
|
| 957 |
-
"organization": "Nexusflow",
|
| 958 |
-
"license": "Apache-2.0",
|
| 959 |
-
"knowledge_cutoff": "2024-01"
|
| 960 |
-
},
|
| 961 |
-
"results": {
|
| 962 |
-
"OVERALL": {
|
| 963 |
-
"Score": 0.479391856,
|
| 964 |
-
"Standard Deviation": 0.04199990887
|
| 965 |
-
},
|
| 966 |
-
"Geometry": {
|
| 967 |
-
"Score": 0.446654388,
|
| 968 |
-
"Standard Deviation": 0.05637864999
|
| 969 |
-
},
|
| 970 |
-
"Algebra": {
|
| 971 |
-
"Score": 0.473952749,
|
| 972 |
-
"Standard Deviation": 0.01584301288
|
| 973 |
-
},
|
| 974 |
-
"Probability": {
|
| 975 |
-
"Score": 0.395197837,
|
| 976 |
-
"Standard Deviation": 0.05814798892
|
| 977 |
-
},
|
| 978 |
-
"Logical": {
|
| 979 |
-
"Score": 0.39927199,
|
| 980 |
-
"Standard Deviation": 0.02125277518
|
| 981 |
-
},
|
| 982 |
-
"Social": {
|
| 983 |
-
"Score": 0.380021662,
|
| 984 |
-
"Standard Deviation": 0.04622452748
|
| 985 |
-
}
|
| 986 |
-
}
|
| 987 |
-
},
|
| 988 |
-
{
|
| 989 |
-
"config": {
|
| 990 |
-
"model_name": "gemini-1.0-pro-001",
|
| 991 |
-
"organization": "Google",
|
| 992 |
-
"license": "Proprietary",
|
| 993 |
-
"knowledge_cutoff": "2023-11"
|
| 994 |
-
},
|
| 995 |
-
"results": {
|
| 996 |
-
"OVERALL": {
|
| 997 |
-
"Score": 0.449040654,
|
| 998 |
-
"Standard Deviation": 0.0450610177
|
| 999 |
-
},
|
| 1000 |
-
"Geometry": {
|
| 1001 |
-
"Score": 0.578347959,
|
| 1002 |
-
"Standard Deviation": 0.04242873607
|
| 1003 |
-
},
|
| 1004 |
-
"Algebra": {
|
| 1005 |
-
"Score": 0.462417786,
|
| 1006 |
-
"Standard Deviation": 0.01668313635
|
| 1007 |
-
},
|
| 1008 |
-
"Probability": {
|
| 1009 |
-
"Score": 0.289836324,
|
| 1010 |
-
"Standard Deviation": 0.05739831115
|
| 1011 |
-
},
|
| 1012 |
-
"Logical": {
|
| 1013 |
-
"Score": 0.191140355,
|
| 1014 |
-
"Standard Deviation": 0.03394652499
|
| 1015 |
-
},
|
| 1016 |
-
"Social": {
|
| 1017 |
-
"Score": 0.130790863,
|
| 1018 |
-
"Standard Deviation": 0.02800188173
|
| 1019 |
-
}
|
| 1020 |
-
}
|
| 1021 |
-
},
|
| 1022 |
-
{
|
| 1023 |
-
"config": {
|
| 1024 |
-
"model_name": "openchat-3.5-0106",
|
| 1025 |
-
"organization": "OpenChat",
|
| 1026 |
-
"license": "Apache-2.0",
|
| 1027 |
-
"knowledge_cutoff": "2024-01"
|
| 1028 |
-
},
|
| 1029 |
-
"results": {
|
| 1030 |
-
"OVERALL": {
|
| 1031 |
-
"Score": 0.363929888,
|
| 1032 |
-
"Standard Deviation": 0.08602347145
|
| 1033 |
-
},
|
| 1034 |
-
"Geometry": {
|
| 1035 |
-
"Score": 0.38715246,
|
| 1036 |
-
"Standard Deviation": 0.03701851946
|
| 1037 |
-
},
|
| 1038 |
-
"Algebra": {
|
| 1039 |
-
"Score": 0.441233712,
|
| 1040 |
-
"Standard Deviation": 0.01135753754
|
| 1041 |
-
},
|
| 1042 |
-
"Probability": {
|
| 1043 |
-
"Score": 0.38802618,
|
| 1044 |
-
"Standard Deviation": 0.05663879714
|
| 1045 |
-
},
|
| 1046 |
-
"Logical": {
|
| 1047 |
-
"Score": 0.336754383,
|
| 1048 |
-
"Standard Deviation": 0.01608478079
|
| 1049 |
-
},
|
| 1050 |
-
"Social": {
|
| 1051 |
-
"Score": 0.250891608,
|
| 1052 |
-
"Standard Deviation": 0.03253769914
|
| 1053 |
-
}
|
| 1054 |
-
}
|
| 1055 |
-
},
|
| 1056 |
-
{
|
| 1057 |
-
"config": {
|
| 1058 |
-
"model_name": "openchat-3.5",
|
| 1059 |
-
"organization": "OpenChat",
|
| 1060 |
-
"license": "Apache-2.0",
|
| 1061 |
-
"knowledge_cutoff": "2023-12"
|
| 1062 |
-
},
|
| 1063 |
-
"results": {
|
| 1064 |
-
"OVERALL": {
|
| 1065 |
-
"Score": 0.361341296,
|
| 1066 |
-
"Standard Deviation": 0.09034869493
|
| 1067 |
-
},
|
| 1068 |
-
"Geometry": {
|
| 1069 |
-
"Score": 0.401699069,
|
| 1070 |
-
"Standard Deviation": 0.03410726557
|
| 1071 |
-
},
|
| 1072 |
-
"Algebra": {
|
| 1073 |
-
"Score": 0.414095336,
|
| 1074 |
-
"Standard Deviation": 0.01881964261
|
| 1075 |
-
},
|
| 1076 |
-
"Probability": {
|
| 1077 |
-
"Score": 0.349601002,
|
| 1078 |
-
"Standard Deviation": 0.05077455539
|
| 1079 |
-
},
|
| 1080 |
-
"Logical": {
|
| 1081 |
-
"Score": 0.331069242,
|
| 1082 |
-
"Standard Deviation": 0.02180827173
|
| 1083 |
-
},
|
| 1084 |
-
"Social": {
|
| 1085 |
-
"Score": 0.319991655,
|
| 1086 |
-
"Standard Deviation": 0.04502478724
|
| 1087 |
-
}
|
| 1088 |
-
}
|
| 1089 |
-
},
|
| 1090 |
-
{
|
| 1091 |
-
"config": {
|
| 1092 |
-
"model_name": "command-r-(08-2024)",
|
| 1093 |
-
"organization": "Cohere",
|
| 1094 |
-
"license": "CC-BY-NC-4.0",
|
| 1095 |
-
"knowledge_cutoff": "2024-08"
|
| 1096 |
-
},
|
| 1097 |
-
"results": {
|
| 1098 |
-
"OVERALL": {
|
| 1099 |
-
"Score": 0.427605298,
|
| 1100 |
-
"Standard Deviation": 0.01747449163
|
| 1101 |
-
},
|
| 1102 |
-
"Geometry": {
|
| 1103 |
-
"Score": 0.448300727,
|
| 1104 |
-
"Standard Deviation": 0.04996362328
|
| 1105 |
-
},
|
| 1106 |
-
"Algebra": {
|
| 1107 |
-
"Score": 0.417519167,
|
| 1108 |
-
"Standard Deviation": 0.01822196902
|
| 1109 |
-
},
|
| 1110 |
-
"Probability": {
|
| 1111 |
-
"Score": 0.366336281,
|
| 1112 |
-
"Standard Deviation": 0.04716826942
|
| 1113 |
-
},
|
| 1114 |
-
"Logical": {
|
| 1115 |
-
"Score": 0.214657906,
|
| 1116 |
-
"Standard Deviation": 0.03003579835
|
| 1117 |
-
},
|
| 1118 |
-
"Social": {
|
| 1119 |
-
"Score": 0.276088379,
|
| 1120 |
-
"Standard Deviation": 0.03295234688
|
| 1121 |
-
}
|
| 1122 |
-
}
|
| 1123 |
-
},
|
| 1124 |
-
{
|
| 1125 |
-
"config": {
|
| 1126 |
-
"model_name": "gemma-1.1-7b-it",
|
| 1127 |
-
"organization": "Google",
|
| 1128 |
-
"license": "Gemma License",
|
| 1129 |
-
"knowledge_cutoff": "2023-11"
|
| 1130 |
-
},
|
| 1131 |
-
"results": {
|
| 1132 |
-
"OVERALL": {
|
| 1133 |
-
"Score": 0.339506922,
|
| 1134 |
-
"Standard Deviation": 0.1066279108
|
| 1135 |
-
},
|
| 1136 |
-
"Geometry": {
|
| 1137 |
-
"Score": 0.324170977,
|
| 1138 |
-
"Standard Deviation": 0.04668553765
|
| 1139 |
-
},
|
| 1140 |
-
"Algebra": {
|
| 1141 |
-
"Score": 0.398684697,
|
| 1142 |
-
"Standard Deviation": 0.01982398259
|
| 1143 |
-
},
|
| 1144 |
-
"Probability": {
|
| 1145 |
-
"Score": 0.293253175,
|
| 1146 |
-
"Standard Deviation": 0.05126192191
|
| 1147 |
-
},
|
| 1148 |
-
"Logical": {
|
| 1149 |
-
"Score": 0.317750796,
|
| 1150 |
-
"Standard Deviation": 0.01101933543
|
| 1151 |
-
},
|
| 1152 |
-
"Social": {
|
| 1153 |
-
"Score": 0.179073276,
|
| 1154 |
-
"Standard Deviation": 0.02009658805
|
| 1155 |
-
}
|
| 1156 |
-
}
|
| 1157 |
-
},
|
| 1158 |
-
{
|
| 1159 |
-
"config": {
|
| 1160 |
-
"model_name": "llama3-8b-instruct",
|
| 1161 |
-
"organization": "Meta",
|
| 1162 |
-
"license": "Llama 3 Community",
|
| 1163 |
-
"knowledge_cutoff": "2024-01"
|
| 1164 |
-
},
|
| 1165 |
-
"results": {
|
| 1166 |
-
"OVERALL": {
|
| 1167 |
-
"Score": 0.367722676,
|
| 1168 |
-
"Standard Deviation": 0.1071368221
|
| 1169 |
-
},
|
| 1170 |
-
"Geometry": {
|
| 1171 |
-
"Score": 0.367143758,
|
| 1172 |
-
"Standard Deviation": 0.04363680358
|
| 1173 |
-
},
|
| 1174 |
-
"Algebra": {
|
| 1175 |
-
"Score": 0.391480973,
|
| 1176 |
-
"Standard Deviation": 0.02757445266
|
| 1177 |
-
},
|
| 1178 |
-
"Probability": {
|
| 1179 |
-
"Score": 0.317616445,
|
| 1180 |
-
"Standard Deviation": 0.04300430361
|
| 1181 |
-
},
|
| 1182 |
-
"Logical": {
|
| 1183 |
-
"Score": 0.461607495,
|
| 1184 |
-
"Standard Deviation": 0.02185028842
|
| 1185 |
-
},
|
| 1186 |
-
"Social": {
|
| 1187 |
-
"Score": 0.336373622,
|
| 1188 |
-
"Standard Deviation": 0.05762408512
|
| 1189 |
-
}
|
| 1190 |
-
}
|
| 1191 |
-
},
|
| 1192 |
-
{
|
| 1193 |
-
"config": {
|
| 1194 |
-
"model_name": "gemma-2-2b-it",
|
| 1195 |
-
"organization": "Google",
|
| 1196 |
-
"license": "Gemma License",
|
| 1197 |
-
"knowledge_cutoff": "2023-12"
|
| 1198 |
-
},
|
| 1199 |
-
"results": {
|
| 1200 |
-
"OVERALL": {
|
| 1201 |
-
"Score": 0.502167612,
|
| 1202 |
-
"Standard Deviation": 0.04389786763
|
| 1203 |
-
},
|
| 1204 |
-
"Geometry": {
|
| 1205 |
-
"Score": 0.395006676,
|
| 1206 |
-
"Standard Deviation": 0.05882607713
|
| 1207 |
-
},
|
| 1208 |
-
"Algebra": {
|
| 1209 |
-
"Score": 0.379391887,
|
| 1210 |
-
"Standard Deviation": 0.01722410785
|
| 1211 |
-
},
|
| 1212 |
-
"Probability": {
|
| 1213 |
-
"Score": 0.331231097,
|
| 1214 |
-
"Standard Deviation": 0.05392499987
|
| 1215 |
-
},
|
| 1216 |
-
"Logical": {
|
| 1217 |
-
"Score": 0.367687789,
|
| 1218 |
-
"Standard Deviation": 0.02547968808
|
| 1219 |
-
},
|
| 1220 |
-
"Social": {
|
| 1221 |
-
"Score": 0.393482094,
|
| 1222 |
-
"Standard Deviation": 0.06450214024
|
| 1223 |
-
}
|
| 1224 |
-
}
|
| 1225 |
-
},
|
| 1226 |
-
{
|
| 1227 |
-
"config": {
|
| 1228 |
-
"model_name": "starling-lm-7b-alpha",
|
| 1229 |
-
"organization": "Nexusflow",
|
| 1230 |
-
"license": "Apache-2.0",
|
| 1231 |
-
"knowledge_cutoff": "2023-12"
|
| 1232 |
-
},
|
| 1233 |
-
"results": {
|
| 1234 |
-
"OVERALL": {
|
| 1235 |
-
"Score": 0.366628765,
|
| 1236 |
-
"Standard Deviation": 0.08405492929
|
| 1237 |
-
},
|
| 1238 |
-
"Geometry": {
|
| 1239 |
-
"Score": 0.336782578,
|
| 1240 |
-
"Standard Deviation": 0.04069449132
|
| 1241 |
-
},
|
| 1242 |
-
"Algebra": {
|
| 1243 |
-
"Score": 0.371551932,
|
| 1244 |
-
"Standard Deviation": 0.03367241745
|
| 1245 |
-
},
|
| 1246 |
-
"Probability": {
|
| 1247 |
-
"Score": 0.331472505,
|
| 1248 |
-
"Standard Deviation": 0.04833324282
|
| 1249 |
-
},
|
| 1250 |
-
"Logical": {
|
| 1251 |
-
"Score": 0.260869624,
|
| 1252 |
-
"Standard Deviation": 0.03562735237
|
| 1253 |
-
},
|
| 1254 |
-
"Social": {
|
| 1255 |
-
"Score": 0.271975534,
|
| 1256 |
-
"Standard Deviation": 0.04266753408
|
| 1257 |
-
}
|
| 1258 |
-
}
|
| 1259 |
-
},
|
| 1260 |
-
{
|
| 1261 |
-
"config": {
|
| 1262 |
-
"model_name": "qwen1.5-4b-chat",
|
| 1263 |
-
"organization": "Alibaba",
|
| 1264 |
-
"license": "Qianwen LICENSE",
|
| 1265 |
-
"knowledge_cutoff": "2024-02"
|
| 1266 |
-
},
|
| 1267 |
-
"results": {
|
| 1268 |
-
"OVERALL": {
|
| 1269 |
-
"Score": 0.111876411,
|
| 1270 |
-
"Standard Deviation": 0.04241022785
|
| 1271 |
-
},
|
| 1272 |
-
"Geometry": {
|
| 1273 |
-
"Score": 0.215834522,
|
| 1274 |
-
"Standard Deviation": 0.0363766363
|
| 1275 |
-
},
|
| 1276 |
-
"Algebra": {
|
| 1277 |
-
"Score": 0.305589811,
|
| 1278 |
-
"Standard Deviation": 0.02354198912
|
| 1279 |
-
},
|
| 1280 |
-
"Probability": {
|
| 1281 |
-
"Score": 0.149365327,
|
| 1282 |
-
"Standard Deviation": 0.03489672675
|
| 1283 |
-
},
|
| 1284 |
-
"Logical": {
|
| 1285 |
-
"Score": 0.116210168,
|
| 1286 |
-
"Standard Deviation": 0.005927966496
|
| 1287 |
-
},
|
| 1288 |
-
"Social": {
|
| 1289 |
-
"Score": 0.18195615,
|
| 1290 |
-
"Standard Deviation": 0.02269805277
|
| 1291 |
-
}
|
| 1292 |
-
}
|
| 1293 |
-
},
|
| 1294 |
-
{
|
| 1295 |
-
"config": {
|
| 1296 |
-
"model_name": "command-r-(04-2024)",
|
| 1297 |
-
"organization": "Cohere",
|
| 1298 |
-
"license": "CC-BY-NC-4.0",
|
| 1299 |
-
"knowledge_cutoff": "2024-04"
|
| 1300 |
-
},
|
| 1301 |
-
"results": {
|
| 1302 |
-
"OVERALL": {
|
| 1303 |
-
"Score": 0.388783887,
|
| 1304 |
-
"Standard Deviation": 0.07417186783
|
| 1305 |
-
},
|
| 1306 |
-
"Geometry": {
|
| 1307 |
-
"Score": 0.300416698,
|
| 1308 |
-
"Standard Deviation": 0.03485612736
|
| 1309 |
-
},
|
| 1310 |
-
"Algebra": {
|
| 1311 |
-
"Score": 0.293120231,
|
| 1312 |
-
"Standard Deviation": 0.032926484
|
| 1313 |
-
},
|
| 1314 |
-
"Probability": {
|
| 1315 |
-
"Score": 0.281271304,
|
| 1316 |
-
"Standard Deviation": 0.05697149867
|
| 1317 |
-
},
|
| 1318 |
-
"Logical": {
|
| 1319 |
-
"Score": 0.276189906,
|
| 1320 |
-
"Standard Deviation": 0.03562914754
|
| 1321 |
-
},
|
| 1322 |
-
"Social": {
|
| 1323 |
-
"Score": 0.283882949,
|
| 1324 |
-
"Standard Deviation": 0.03336901148
|
| 1325 |
-
}
|
| 1326 |
-
}
|
| 1327 |
-
},
|
| 1328 |
-
{
|
| 1329 |
-
"config": {
|
| 1330 |
-
"model_name": "vicuna-33b",
|
| 1331 |
-
"organization": "LMSYS",
|
| 1332 |
-
"license": "Non-commercial",
|
| 1333 |
-
"knowledge_cutoff": "2023-12"
|
| 1334 |
-
},
|
| 1335 |
-
"results": {
|
| 1336 |
-
"OVERALL": {
|
| 1337 |
-
"Score": 0.316543555,
|
| 1338 |
-
"Standard Deviation": 0.08922095647
|
| 1339 |
-
},
|
| 1340 |
-
"Geometry": {
|
| 1341 |
-
"Score": 0.208284679,
|
| 1342 |
-
"Standard Deviation": 0.03937771461
|
| 1343 |
-
},
|
| 1344 |
-
"Algebra": {
|
| 1345 |
-
"Score": 0.248994048,
|
| 1346 |
-
"Standard Deviation": 0.02668175054
|
| 1347 |
-
},
|
| 1348 |
-
"Probability": {
|
| 1349 |
-
"Score": 0.222313995,
|
| 1350 |
-
"Standard Deviation": 0.03978859759
|
| 1351 |
-
},
|
| 1352 |
-
"Logical": {
|
| 1353 |
-
"Score": 0.180291222,
|
| 1354 |
-
"Standard Deviation": 0.021886267
|
| 1355 |
-
},
|
| 1356 |
-
"Social": {
|
| 1357 |
-
"Score": 0.257623798,
|
| 1358 |
-
"Standard Deviation": 0.02653724437
|
| 1359 |
-
}
|
| 1360 |
-
}
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"config": {
|
| 1364 |
-
"model_name": "gemma-7b-it",
|
| 1365 |
-
"organization": "Google",
|
| 1366 |
-
"license": "Gemma License",
|
| 1367 |
-
"knowledge_cutoff": "2023-12"
|
| 1368 |
-
},
|
| 1369 |
-
"results": {
|
| 1370 |
-
"OVERALL": {
|
| 1371 |
-
"Score": 0.285077558,
|
| 1372 |
-
"Standard Deviation": 0.08871758453
|
| 1373 |
-
},
|
| 1374 |
-
"Geometry": {
|
| 1375 |
-
"Score": 0.244791417,
|
| 1376 |
-
"Standard Deviation": 0.0289612078
|
| 1377 |
-
},
|
| 1378 |
-
"Algebra": {
|
| 1379 |
-
"Score": 0.250614794,
|
| 1380 |
-
"Standard Deviation": 0.01991678295
|
| 1381 |
-
},
|
| 1382 |
-
"Probability": {
|
| 1383 |
-
"Score": 0.174313053,
|
| 1384 |
-
"Standard Deviation": 0.03765424728
|
| 1385 |
-
},
|
| 1386 |
-
"Logical": {
|
| 1387 |
-
"Score": 0.197505536,
|
| 1388 |
-
"Standard Deviation": 0.02050298885
|
| 1389 |
-
},
|
| 1390 |
-
"Social": {
|
| 1391 |
-
"Score": 0.202138025,
|
| 1392 |
-
"Standard Deviation": 0.02098346639
|
| 1393 |
-
}
|
| 1394 |
-
}
|
| 1395 |
-
},
|
| 1396 |
-
{
|
| 1397 |
-
"config": {
|
| 1398 |
-
"model_name": "mistral-7b-instruct-2",
|
| 1399 |
-
"organization": "Mistral",
|
| 1400 |
-
"license": "Apache 2.0",
|
| 1401 |
-
"knowledge_cutoff": "2023-12"
|
| 1402 |
-
},
|
| 1403 |
-
"results": {
|
| 1404 |
-
"OVERALL": {
|
| 1405 |
-
"Score": 0.427513868,
|
| 1406 |
-
"Standard Deviation": 0.05553921135
|
| 1407 |
-
},
|
| 1408 |
-
"Geometry": {
|
| 1409 |
-
"Score": 0.216402626,
|
| 1410 |
-
"Standard Deviation": 0.03338414918
|
| 1411 |
-
},
|
| 1412 |
-
"Algebra": {
|
| 1413 |
-
"Score": 0.233777838,
|
| 1414 |
-
"Standard Deviation": 0.0155226054
|
| 1415 |
-
},
|
| 1416 |
-
"Probability": {
|
| 1417 |
-
"Score": 0.25118175,
|
| 1418 |
-
"Standard Deviation": 0.04065514593
|
| 1419 |
-
},
|
| 1420 |
-
"Logical": {
|
| 1421 |
-
"Score": 0.224469136,
|
| 1422 |
-
"Standard Deviation": 0.03404706752
|
| 1423 |
-
},
|
| 1424 |
-
"Social": {
|
| 1425 |
-
"Score": 0.209386782,
|
| 1426 |
-
"Standard Deviation": 0.02738569921
|
| 1427 |
-
}
|
| 1428 |
-
}
|
| 1429 |
-
},
|
| 1430 |
-
{
|
| 1431 |
-
"config": {
|
| 1432 |
-
"model_name": "mistral-7b-instruct-1",
|
| 1433 |
-
"organization": "Mistral",
|
| 1434 |
-
"license": "Apache 2.0",
|
| 1435 |
-
"knowledge_cutoff": "2023-12"
|
| 1436 |
-
},
|
| 1437 |
-
"results": {
|
| 1438 |
-
"OVERALL": {
|
| 1439 |
-
"Score": 0.23016314,
|
| 1440 |
-
"Standard Deviation": 0.07137625271
|
| 1441 |
-
},
|
| 1442 |
-
"Geometry": {
|
| 1443 |
-
"Score": 0.161799938,
|
| 1444 |
-
"Standard Deviation": 0.03595278559
|
| 1445 |
-
},
|
| 1446 |
-
"Algebra": {
|
| 1447 |
-
"Score": 0.210341624,
|
| 1448 |
-
"Standard Deviation": 0.01736539119
|
| 1449 |
-
},
|
| 1450 |
-
"Probability": {
|
| 1451 |
-
"Score": 0.238417922,
|
| 1452 |
-
"Standard Deviation": 0.03744211933
|
| 1453 |
-
},
|
| 1454 |
-
"Logical": {
|
| 1455 |
-
"Score": 0.142636601,
|
| 1456 |
-
"Standard Deviation": 0.02080406365
|
| 1457 |
-
},
|
| 1458 |
-
"Social": {
|
| 1459 |
-
"Score": 0.117646827,
|
| 1460 |
-
"Standard Deviation": 0.009321202779
|
| 1461 |
-
}
|
| 1462 |
-
}
|
| 1463 |
-
},
|
| 1464 |
-
{
|
| 1465 |
-
"config": {
|
| 1466 |
-
"model_name": "vicuna-13b",
|
| 1467 |
-
"organization": "LMSYS",
|
| 1468 |
-
"license": "Non-commercial",
|
| 1469 |
-
"knowledge_cutoff": "2023-11"
|
| 1470 |
-
},
|
| 1471 |
-
"results": {
|
| 1472 |
-
"OVERALL": {
|
| 1473 |
-
"Score": 0.201892849,
|
| 1474 |
-
"Standard Deviation": 0.06021749802
|
| 1475 |
-
},
|
| 1476 |
-
"Geometry": {
|
| 1477 |
-
"Score": 0.200941928,
|
| 1478 |
-
"Standard Deviation": 0.03366817781
|
| 1479 |
-
},
|
| 1480 |
-
"Algebra": {
|
| 1481 |
-
"Score": 0.196123323,
|
| 1482 |
-
"Standard Deviation": 0.0135715643
|
| 1483 |
-
},
|
| 1484 |
-
"Probability": {
|
| 1485 |
-
"Score": 0.141214079,
|
| 1486 |
-
"Standard Deviation": 0.02721328211
|
| 1487 |
-
},
|
| 1488 |
-
"Logical": {
|
| 1489 |
-
"Score": 0.148598631,
|
| 1490 |
-
"Standard Deviation": 0.02241523892
|
| 1491 |
-
},
|
| 1492 |
-
"Social": {
|
| 1493 |
-
"Score": 0.124655135,
|
| 1494 |
-
"Standard Deviation": 0.01122382671
|
| 1495 |
-
}
|
| 1496 |
-
}
|
| 1497 |
-
},
|
| 1498 |
-
{
|
| 1499 |
-
"config": {
|
| 1500 |
-
"model_name": "zephyr-7b-beta",
|
| 1501 |
-
"organization": "HuggingFace",
|
| 1502 |
-
"license": "MIT",
|
| 1503 |
-
"knowledge_cutoff": "2023-10"
|
| 1504 |
-
},
|
| 1505 |
-
"results": {
|
| 1506 |
-
"OVERALL": {
|
| 1507 |
-
"Score": 0.102705119,
|
| 1508 |
-
"Standard Deviation": 0.03683757312
|
| 1509 |
-
},
|
| 1510 |
-
"Geometry": {
|
| 1511 |
-
"Score": 0.114005544,
|
| 1512 |
-
"Standard Deviation": 0.03144354365
|
| 1513 |
-
},
|
| 1514 |
-
"Algebra": {
|
| 1515 |
-
"Score": 0.141766633,
|
| 1516 |
-
"Standard Deviation": 0.03179520129
|
| 1517 |
-
},
|
| 1518 |
-
"Probability": {
|
| 1519 |
-
"Score": 0.089050714,
|
| 1520 |
-
"Standard Deviation": 0.002136754266
|
| 1521 |
-
},
|
| 1522 |
-
"Logical": {
|
| 1523 |
-
"Score": 0.069520789,
|
| 1524 |
-
"Standard Deviation": 0.004477840857
|
| 1525 |
-
},
|
| 1526 |
-
"Social": {
|
| 1527 |
-
"Score": 0.0,
|
| 1528 |
-
"Standard Deviation": 0.0
|
| 1529 |
-
}
|
| 1530 |
-
}
|
| 1531 |
-
},
|
| 1532 |
-
{
|
| 1533 |
-
"config": {
|
| 1534 |
-
"model_name": "gemma-1.1-2b-it",
|
| 1535 |
-
"organization": "Google",
|
| 1536 |
-
"license": "Gemma License",
|
| 1537 |
-
"knowledge_cutoff": "2023-12"
|
| 1538 |
-
},
|
| 1539 |
-
"results": {
|
| 1540 |
-
"OVERALL": {
|
| 1541 |
-
"Score": 0.257700845,
|
| 1542 |
-
"Standard Deviation": 0.07369021445
|
| 1543 |
-
},
|
| 1544 |
-
"Geometry": {
|
| 1545 |
-
"Score": 0.183974034,
|
| 1546 |
-
"Standard Deviation": 0.0215548886
|
| 1547 |
-
},
|
| 1548 |
-
"Algebra": {
|
| 1549 |
-
"Score": 0.13422252,
|
| 1550 |
-
"Standard Deviation": 0.01922819511
|
| 1551 |
-
},
|
| 1552 |
-
"Probability": {
|
| 1553 |
-
"Score": 0.095628657,
|
| 1554 |
-
"Standard Deviation": 0.007536076456
|
| 1555 |
-
},
|
| 1556 |
-
"Logical": {
|
| 1557 |
-
"Score": 0.094965074,
|
| 1558 |
-
"Standard Deviation": 0.005019175487
|
| 1559 |
-
},
|
| 1560 |
-
"Social": {
|
| 1561 |
-
"Score": 0.167796727,
|
| 1562 |
-
"Standard Deviation": 0.01666541942
|
| 1563 |
-
}
|
| 1564 |
-
}
|
| 1565 |
-
},
|
| 1566 |
-
{
|
| 1567 |
-
"config": {
|
| 1568 |
-
"model_name": "llama2-7b-chat",
|
| 1569 |
-
"organization": "Meta",
|
| 1570 |
-
"license": "Llama 2 Community",
|
| 1571 |
-
"knowledge_cutoff": "2023-10"
|
| 1572 |
-
},
|
| 1573 |
-
"results": {
|
| 1574 |
-
"OVERALL": {
|
| 1575 |
-
"Score": 0.260189428,
|
| 1576 |
-
"Standard Deviation": 0.08019299364
|
| 1577 |
-
},
|
| 1578 |
-
"Geometry": {
|
| 1579 |
-
"Score": 0.087067276,
|
| 1580 |
-
"Standard Deviation": 0.04274343402
|
| 1581 |
-
},
|
| 1582 |
-
"Algebra": {
|
| 1583 |
-
"Score": 0.12308805,
|
| 1584 |
-
"Standard Deviation": 0.01856053622
|
| 1585 |
-
},
|
| 1586 |
-
"Probability": {
|
| 1587 |
-
"Score": 0.087515438,
|
| 1588 |
-
"Standard Deviation": 0.006315053573
|
| 1589 |
-
},
|
| 1590 |
-
"Logical": {
|
| 1591 |
-
"Score": 0.17312827,
|
| 1592 |
-
"Standard Deviation": 0.01867044092
|
| 1593 |
-
},
|
| 1594 |
-
"Social": {
|
| 1595 |
-
"Score": 0.152905272,
|
| 1596 |
-
"Standard Deviation": 0.007166957097
|
| 1597 |
-
}
|
| 1598 |
-
}
|
| 1599 |
-
},
|
| 1600 |
-
{
|
| 1601 |
-
"config": {
|
| 1602 |
-
"model_name": "gemma-2b-it",
|
| 1603 |
-
"organization": "Google",
|
| 1604 |
-
"license": "Gemma License",
|
| 1605 |
-
"knowledge_cutoff": "2023-11"
|
| 1606 |
-
},
|
| 1607 |
-
"results": {
|
| 1608 |
-
"OVERALL": {
|
| 1609 |
-
"Score": 0.234172069,
|
| 1610 |
-
"Standard Deviation": 0.06522685718
|
| 1611 |
-
},
|
| 1612 |
-
"Geometry": {
|
| 1613 |
-
"Score": 0.198571153,
|
| 1614 |
-
"Standard Deviation": 0.01699161031
|
| 1615 |
-
},
|
| 1616 |
-
"Algebra": {
|
| 1617 |
-
"Score": 0.109883009,
|
| 1618 |
-
"Standard Deviation": 0.01520005833
|
| 1619 |
-
},
|
| 1620 |
-
"Probability": {
|
| 1621 |
-
"Score": 0.06467432,
|
| 1622 |
-
"Standard Deviation": 0.002117497231
|
| 1623 |
-
},
|
| 1624 |
-
"Logical": {
|
| 1625 |
-
"Score": 0.039624492,
|
| 1626 |
-
"Standard Deviation": 0.007606972686
|
| 1627 |
-
},
|
| 1628 |
-
"Social": {
|
| 1629 |
-
"Score": 0.087452913,
|
| 1630 |
-
"Standard Deviation": 0.008170146562
|
| 1631 |
-
}
|
| 1632 |
-
}
|
| 1633 |
-
},
|
| 1634 |
-
{
|
| 1635 |
-
"config": {
|
| 1636 |
-
"model_name": "llama2-13b-chat",
|
| 1637 |
-
"organization": "Meta",
|
| 1638 |
-
"license": "Llama 2 Community",
|
| 1639 |
-
"knowledge_cutoff": "2023-12"
|
| 1640 |
-
},
|
| 1641 |
-
"results": {
|
| 1642 |
-
"OVERALL": {
|
| 1643 |
-
"Score": 0.263305684,
|
| 1644 |
-
"Standard Deviation": 0.07283640689
|
| 1645 |
-
},
|
| 1646 |
-
"Geometry": {
|
| 1647 |
-
"Score": 0.072729954,
|
| 1648 |
-
"Standard Deviation": 0.02315988261
|
| 1649 |
-
},
|
| 1650 |
-
"Algebra": {
|
| 1651 |
-
"Score": 0.080371692,
|
| 1652 |
-
"Standard Deviation": 0.01277569453
|
| 1653 |
-
},
|
| 1654 |
-
"Probability": {
|
| 1655 |
-
"Score": 0.117757344,
|
| 1656 |
-
"Standard Deviation": 0.02418619619
|
| 1657 |
-
},
|
| 1658 |
-
"Logical": {
|
| 1659 |
-
"Score": 0.193149889,
|
| 1660 |
-
"Standard Deviation": 0.01776690764
|
| 1661 |
-
},
|
| 1662 |
-
"Social": {
|
| 1663 |
-
"Score": 0.149125922,
|
| 1664 |
-
"Standard Deviation": 0.01157416827
|
| 1665 |
-
}
|
| 1666 |
-
}
|
| 1667 |
-
},
|
| 1668 |
-
{
|
| 1669 |
-
"config": {
|
| 1670 |
-
"model_name": "vicuna-7b",
|
| 1671 |
-
"organization": "LMSYS",
|
| 1672 |
-
"license": "Non-commercial",
|
| 1673 |
-
"knowledge_cutoff": "2023-11"
|
| 1674 |
-
},
|
| 1675 |
-
"results": {
|
| 1676 |
-
"OVERALL": {
|
| 1677 |
-
"Score": 0.198839786,
|
| 1678 |
-
"Standard Deviation": 0.05725381576
|
| 1679 |
-
},
|
| 1680 |
-
"Geometry": {
|
| 1681 |
-
"Score": 0.083457058,
|
| 1682 |
-
"Standard Deviation": 0.02520989111
|
| 1683 |
-
},
|
| 1684 |
-
"Algebra": {
|
| 1685 |
-
"Score": 0.070883882,
|
| 1686 |
-
"Standard Deviation": 0.007315853253
|
| 1687 |
-
},
|
| 1688 |
-
"Probability": {
|
| 1689 |
-
"Score": 0.080987673,
|
| 1690 |
-
"Standard Deviation": 0.005474288861
|
| 1691 |
-
},
|
| 1692 |
-
"Logical": {
|
| 1693 |
-
"Score": 0.100065588,
|
| 1694 |
-
"Standard Deviation": 0.003561886452
|
| 1695 |
-
},
|
| 1696 |
-
"Social": {
|
| 1697 |
-
"Score": 0.111076414,
|
| 1698 |
-
"Standard Deviation": 0.004805626512
|
| 1699 |
-
}
|
| 1700 |
-
}
|
| 1701 |
-
},
|
| 1702 |
-
{
|
| 1703 |
-
"config": {
|
| 1704 |
-
"model_name": "koala-13b",
|
| 1705 |
-
"organization": "UC Berkeley",
|
| 1706 |
-
"license": "Non-commercial",
|
| 1707 |
-
"knowledge_cutoff": "2023-10"
|
| 1708 |
-
},
|
| 1709 |
-
"results": {
|
| 1710 |
-
"OVERALL": {
|
| 1711 |
-
"Score": 0.09387188,
|
| 1712 |
-
"Standard Deviation": 0.02642167489
|
| 1713 |
-
},
|
| 1714 |
-
"Geometry": {
|
| 1715 |
-
"Score": 0.017374001,
|
| 1716 |
-
"Standard Deviation": 0.01747053557
|
| 1717 |
-
},
|
| 1718 |
-
"Algebra": {
|
| 1719 |
-
"Score": 0.018129197,
|
| 1720 |
-
"Standard Deviation": 0.01054371383
|
| 1721 |
-
},
|
| 1722 |
-
"Probability": {
|
| 1723 |
-
"Score": 0.043654362,
|
| 1724 |
-
"Standard Deviation": 0.004288231886
|
| 1725 |
-
},
|
| 1726 |
-
"Logical": {
|
| 1727 |
-
"Score": 0.074694053,
|
| 1728 |
-
"Standard Deviation": 0.002674646998
|
| 1729 |
-
},
|
| 1730 |
-
"Social": {
|
| 1731 |
-
"Score": 0.096983835,
|
| 1732 |
-
"Standard Deviation": 0.007847059783
|
| 1733 |
-
}
|
| 1734 |
-
}
|
| 1735 |
-
},
|
| 1736 |
-
{
|
| 1737 |
-
"config": {
|
| 1738 |
-
"model_name": "openassistant-pythia-12b",
|
| 1739 |
-
"organization": "OpenAssistant",
|
| 1740 |
-
"license": "Non-commercial",
|
| 1741 |
-
"knowledge_cutoff": "2023-09"
|
| 1742 |
-
},
|
| 1743 |
-
"results": {
|
| 1744 |
-
"OVERALL": {
|
| 1745 |
-
"Score": 0.0,
|
| 1746 |
-
"Standard Deviation": 0.0
|
| 1747 |
-
},
|
| 1748 |
-
"Geometry": {
|
| 1749 |
-
"Score": 0.0,
|
| 1750 |
-
"Standard Deviation": 0.0
|
| 1751 |
-
},
|
| 1752 |
-
"Algebra": {
|
| 1753 |
-
"Score": 0.0,
|
| 1754 |
-
"Standard Deviation": 0.0
|
| 1755 |
-
},
|
| 1756 |
-
"Probability": {
|
| 1757 |
-
"Score": 0.0,
|
| 1758 |
-
"Standard Deviation": 0.0
|
| 1759 |
-
},
|
| 1760 |
-
"Logical": {
|
| 1761 |
-
"Score": 0.0,
|
| 1762 |
-
"Standard Deviation": 0.0
|
| 1763 |
-
},
|
| 1764 |
-
"Social": {
|
| 1765 |
-
"Score": 0.030792528,
|
| 1766 |
-
"Standard Deviation": 0.007518796391
|
| 1767 |
-
}
|
| 1768 |
-
}
|
| 1769 |
-
}
|
| 1770 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/models_2024-10-08-03:25:44.801310.jsonl
DELETED
|
@@ -1,2082 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"config": {
|
| 4 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 5 |
-
"organization": "OpenAI",
|
| 6 |
-
"license": "Proprietary",
|
| 7 |
-
"knowledge_cutoff": "2023/10"
|
| 8 |
-
},
|
| 9 |
-
"results": {
|
| 10 |
-
"OVERALL": {
|
| 11 |
-
"Average Score": 0.974329609,
|
| 12 |
-
"Standard Deviation": 0.005024959031,
|
| 13 |
-
"Rank": 2
|
| 14 |
-
},
|
| 15 |
-
"Geometry": {
|
| 16 |
-
"Average Score": 0.976028578,
|
| 17 |
-
"Standard Deviation": 0.01507912373,
|
| 18 |
-
"Rank": 3
|
| 19 |
-
},
|
| 20 |
-
"Algebra": {
|
| 21 |
-
"Average Score": 0.951199453,
|
| 22 |
-
"Standard Deviation": 0.08452452108,
|
| 23 |
-
"Rank": 3
|
| 24 |
-
},
|
| 25 |
-
"Probability": {
|
| 26 |
-
"Average Score": 0.842116641,
|
| 27 |
-
"Standard Deviation": 0.006267759054,
|
| 28 |
-
"Rank": 3
|
| 29 |
-
},
|
| 30 |
-
"Logical": {
|
| 31 |
-
"Average Score": 0.828490728,
|
| 32 |
-
"Standard Deviation": 0.009134213144,
|
| 33 |
-
"Rank": 3
|
| 34 |
-
},
|
| 35 |
-
"Social": {
|
| 36 |
-
"Average Score": 0.815902987,
|
| 37 |
-
"Standard Deviation": 0.0196254222,
|
| 38 |
-
"Rank": 4
|
| 39 |
-
}
|
| 40 |
-
}
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"config": {
|
| 44 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 45 |
-
"organization": "OpenAI",
|
| 46 |
-
"license": "Proprietary",
|
| 47 |
-
"knowledge_cutoff": "2023/10"
|
| 48 |
-
},
|
| 49 |
-
"results": {
|
| 50 |
-
"OVERALL": {
|
| 51 |
-
"Average Score": 0.846571548,
|
| 52 |
-
"Standard Deviation": 0.03394056554,
|
| 53 |
-
"Rank": 6
|
| 54 |
-
},
|
| 55 |
-
"Geometry": {
|
| 56 |
-
"Average Score": 0.99773096,
|
| 57 |
-
"Standard Deviation": 0.002835555172,
|
| 58 |
-
"Rank": 1
|
| 59 |
-
},
|
| 60 |
-
"Algebra": {
|
| 61 |
-
"Average Score": 1.0,
|
| 62 |
-
"Standard Deviation": 0.0,
|
| 63 |
-
"Rank": 1
|
| 64 |
-
},
|
| 65 |
-
"Probability": {
|
| 66 |
-
"Average Score": 0.78855795,
|
| 67 |
-
"Standard Deviation": 0.008188675452,
|
| 68 |
-
"Rank": 6
|
| 69 |
-
},
|
| 70 |
-
"Logical": {
|
| 71 |
-
"Average Score": 0.668635768,
|
| 72 |
-
"Standard Deviation": 0.03466314094,
|
| 73 |
-
"Rank": 11
|
| 74 |
-
},
|
| 75 |
-
"Social": {
|
| 76 |
-
"Average Score": 0.680417314,
|
| 77 |
-
"Standard Deviation": 0.00656867063,
|
| 78 |
-
"Rank": 9
|
| 79 |
-
}
|
| 80 |
-
}
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"config": {
|
| 84 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 85 |
-
"organization": "OpenAI",
|
| 86 |
-
"license": "Proprietary",
|
| 87 |
-
"knowledge_cutoff": "2023/10"
|
| 88 |
-
},
|
| 89 |
-
"results": {
|
| 90 |
-
"OVERALL": {
|
| 91 |
-
"Average Score": 0.846334477,
|
| 92 |
-
"Standard Deviation": 0.09377911572,
|
| 93 |
-
"Rank": 7
|
| 94 |
-
},
|
| 95 |
-
"Geometry": {
|
| 96 |
-
"Average Score": 0.972472377,
|
| 97 |
-
"Standard Deviation": 0.01648274205,
|
| 98 |
-
"Rank": 4
|
| 99 |
-
},
|
| 100 |
-
"Algebra": {
|
| 101 |
-
"Average Score": 0.995511298,
|
| 102 |
-
"Standard Deviation": 0.004097802515,
|
| 103 |
-
"Rank": 2
|
| 104 |
-
},
|
| 105 |
-
"Probability": {
|
| 106 |
-
"Average Score": 0.812149974,
|
| 107 |
-
"Standard Deviation": 0.007669585485,
|
| 108 |
-
"Rank": 4
|
| 109 |
-
},
|
| 110 |
-
"Logical": {
|
| 111 |
-
"Average Score": 0.755019692,
|
| 112 |
-
"Standard Deviation": 0.008149588572,
|
| 113 |
-
"Rank": 6
|
| 114 |
-
},
|
| 115 |
-
"Social": {
|
| 116 |
-
"Average Score": 0.609875087,
|
| 117 |
-
"Standard Deviation": 0.038729239,
|
| 118 |
-
"Rank": 14
|
| 119 |
-
}
|
| 120 |
-
}
|
| 121 |
-
},
|
| 122 |
-
{
|
| 123 |
-
"config": {
|
| 124 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 125 |
-
"organization": "OpenAI",
|
| 126 |
-
"license": "Proprietary",
|
| 127 |
-
"knowledge_cutoff": "2023/12"
|
| 128 |
-
},
|
| 129 |
-
"results": {
|
| 130 |
-
"OVERALL": {
|
| 131 |
-
"Average Score": 0.855357972,
|
| 132 |
-
"Standard Deviation": 0.1016986368,
|
| 133 |
-
"Rank": 4
|
| 134 |
-
},
|
| 135 |
-
"Geometry": {
|
| 136 |
-
"Average Score": 0.95374588,
|
| 137 |
-
"Standard Deviation": 0.03109307166,
|
| 138 |
-
"Rank": 5
|
| 139 |
-
},
|
| 140 |
-
"Algebra": {
|
| 141 |
-
"Average Score": 0.930945223,
|
| 142 |
-
"Standard Deviation": 0.06705136813,
|
| 143 |
-
"Rank": 4
|
| 144 |
-
},
|
| 145 |
-
"Probability": {
|
| 146 |
-
"Average Score": 0.750705448,
|
| 147 |
-
"Standard Deviation": 0.05944483103,
|
| 148 |
-
"Rank": 8
|
| 149 |
-
},
|
| 150 |
-
"Logical": {
|
| 151 |
-
"Average Score": 0.77906699,
|
| 152 |
-
"Standard Deviation": 0.007406734161,
|
| 153 |
-
"Rank": 4
|
| 154 |
-
},
|
| 155 |
-
"Social": {
|
| 156 |
-
"Average Score": 0.715935163,
|
| 157 |
-
"Standard Deviation": 0.1209141409,
|
| 158 |
-
"Rank": 7
|
| 159 |
-
}
|
| 160 |
-
}
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"config": {
|
| 164 |
-
"model_name": "gemini-1.5-pro-001",
|
| 165 |
-
"organization": "Google",
|
| 166 |
-
"license": "Proprietary",
|
| 167 |
-
"knowledge_cutoff": "2024-01"
|
| 168 |
-
},
|
| 169 |
-
"results": {
|
| 170 |
-
"OVERALL": {
|
| 171 |
-
"Average Score": 0.797187842,
|
| 172 |
-
"Standard Deviation": 0.0272375249,
|
| 173 |
-
"Rank": 10
|
| 174 |
-
},
|
| 175 |
-
"Geometry": {
|
| 176 |
-
"Average Score": 0.9947169,
|
| 177 |
-
"Standard Deviation": 0.009150597621,
|
| 178 |
-
"Rank": 2
|
| 179 |
-
},
|
| 180 |
-
"Algebra": {
|
| 181 |
-
"Average Score": 0.857464301,
|
| 182 |
-
"Standard Deviation": 0.05014285338,
|
| 183 |
-
"Rank": 5
|
| 184 |
-
},
|
| 185 |
-
"Probability": {
|
| 186 |
-
"Average Score": 0.651781767,
|
| 187 |
-
"Standard Deviation": 0.04156998547,
|
| 188 |
-
"Rank": 12
|
| 189 |
-
},
|
| 190 |
-
"Logical": {
|
| 191 |
-
"Average Score": 0.739745471,
|
| 192 |
-
"Standard Deviation": 0.01631532019,
|
| 193 |
-
"Rank": 7
|
| 194 |
-
},
|
| 195 |
-
"Social": {
|
| 196 |
-
"Average Score": 0.649601885,
|
| 197 |
-
"Standard Deviation": 0.104854889,
|
| 198 |
-
"Rank": 12
|
| 199 |
-
}
|
| 200 |
-
}
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"config": {
|
| 204 |
-
"model_name": "qwen2-72b-instruct",
|
| 205 |
-
"organization": "Alibaba",
|
| 206 |
-
"license": "Qianwen LICENSE",
|
| 207 |
-
"knowledge_cutoff": "2024-02"
|
| 208 |
-
},
|
| 209 |
-
"results": {
|
| 210 |
-
"OVERALL": {
|
| 211 |
-
"Average Score": 0.737918558,
|
| 212 |
-
"Standard Deviation": 0.09069077339,
|
| 213 |
-
"Rank": 11
|
| 214 |
-
},
|
| 215 |
-
"Geometry": {
|
| 216 |
-
"Average Score": 0.796870305,
|
| 217 |
-
"Standard Deviation": 0.0509025346,
|
| 218 |
-
"Rank": 9
|
| 219 |
-
},
|
| 220 |
-
"Algebra": {
|
| 221 |
-
"Average Score": 0.836194231,
|
| 222 |
-
"Standard Deviation": 0.04517093028,
|
| 223 |
-
"Rank": 6
|
| 224 |
-
},
|
| 225 |
-
"Probability": {
|
| 226 |
-
"Average Score": 0.788068004,
|
| 227 |
-
"Standard Deviation": 0.007288989044,
|
| 228 |
-
"Rank": 7
|
| 229 |
-
},
|
| 230 |
-
"Logical": {
|
| 231 |
-
"Average Score": 0.619300904,
|
| 232 |
-
"Standard Deviation": 0.06377931612,
|
| 233 |
-
"Rank": 15
|
| 234 |
-
},
|
| 235 |
-
"Social": {
|
| 236 |
-
"Average Score": 0.652578786,
|
| 237 |
-
"Standard Deviation": 0.04259293171,
|
| 238 |
-
"Rank": 11
|
| 239 |
-
}
|
| 240 |
-
}
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"config": {
|
| 244 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 245 |
-
"organization": "OpenAI",
|
| 246 |
-
"license": "Proprietary",
|
| 247 |
-
"knowledge_cutoff": "2024-07"
|
| 248 |
-
},
|
| 249 |
-
"results": {
|
| 250 |
-
"OVERALL": {
|
| 251 |
-
"Average Score": 0.847694133,
|
| 252 |
-
"Standard Deviation": 0.02164304402,
|
| 253 |
-
"Rank": 5
|
| 254 |
-
},
|
| 255 |
-
"Geometry": {
|
| 256 |
-
"Average Score": 0.946650435,
|
| 257 |
-
"Standard Deviation": 0.01831236482,
|
| 258 |
-
"Rank": 7
|
| 259 |
-
},
|
| 260 |
-
"Algebra": {
|
| 261 |
-
"Average Score": 0.796243022,
|
| 262 |
-
"Standard Deviation": 0.05537539202,
|
| 263 |
-
"Rank": 7
|
| 264 |
-
},
|
| 265 |
-
"Probability": {
|
| 266 |
-
"Average Score": 0.798402685,
|
| 267 |
-
"Standard Deviation": 0.009404491967,
|
| 268 |
-
"Rank": 5
|
| 269 |
-
},
|
| 270 |
-
"Logical": {
|
| 271 |
-
"Average Score": 0.727009735,
|
| 272 |
-
"Standard Deviation": 0.02628110141,
|
| 273 |
-
"Rank": 8
|
| 274 |
-
},
|
| 275 |
-
"Social": {
|
| 276 |
-
"Average Score": 0.691949855,
|
| 277 |
-
"Standard Deviation": 0.02072934333,
|
| 278 |
-
"Rank": 8
|
| 279 |
-
}
|
| 280 |
-
}
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"config": {
|
| 284 |
-
"model_name": "claude-3.5-sonnet",
|
| 285 |
-
"organization": "Anthropic",
|
| 286 |
-
"license": "Proprietary",
|
| 287 |
-
"knowledge_cutoff": "2024-03"
|
| 288 |
-
},
|
| 289 |
-
"results": {
|
| 290 |
-
"OVERALL": {
|
| 291 |
-
"Average Score": 0.839004422,
|
| 292 |
-
"Standard Deviation": 0.1461079564,
|
| 293 |
-
"Rank": 8
|
| 294 |
-
},
|
| 295 |
-
"Geometry": {
|
| 296 |
-
"Average Score": 0.95316419,
|
| 297 |
-
"Standard Deviation": 0.02081192856,
|
| 298 |
-
"Rank": 6
|
| 299 |
-
},
|
| 300 |
-
"Algebra": {
|
| 301 |
-
"Average Score": 0.759789952,
|
| 302 |
-
"Standard Deviation": 0.02611765096,
|
| 303 |
-
"Rank": 8
|
| 304 |
-
},
|
| 305 |
-
"Probability": {
|
| 306 |
-
"Average Score": 0.707730127,
|
| 307 |
-
"Standard Deviation": 0.0394436664,
|
| 308 |
-
"Rank": 10
|
| 309 |
-
},
|
| 310 |
-
"Logical": {
|
| 311 |
-
"Average Score": 0.77342666,
|
| 312 |
-
"Standard Deviation": 0.002892426458,
|
| 313 |
-
"Rank": 5
|
| 314 |
-
},
|
| 315 |
-
"Social": {
|
| 316 |
-
"Average Score": 0.790002247,
|
| 317 |
-
"Standard Deviation": 0.1007410022,
|
| 318 |
-
"Rank": 5
|
| 319 |
-
}
|
| 320 |
-
}
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"config": {
|
| 324 |
-
"model_name": "o1-mini",
|
| 325 |
-
"organization": "OpenAI",
|
| 326 |
-
"license": "Proprietary",
|
| 327 |
-
"knowledge_cutoff": "2024-01"
|
| 328 |
-
},
|
| 329 |
-
"results": {
|
| 330 |
-
"OVERALL": {
|
| 331 |
-
"Average Score": 1.0,
|
| 332 |
-
"Standard Deviation": 0.0,
|
| 333 |
-
"Rank": 1
|
| 334 |
-
},
|
| 335 |
-
"Geometry": {
|
| 336 |
-
"Average Score": "N/A",
|
| 337 |
-
"Standard Deviation": "N/A",
|
| 338 |
-
"Rank": "N/A"
|
| 339 |
-
},
|
| 340 |
-
"Algebra": {
|
| 341 |
-
"Average Score": "N/A",
|
| 342 |
-
"Standard Deviation": "N/A",
|
| 343 |
-
"Rank": "N/A"
|
| 344 |
-
},
|
| 345 |
-
"Probability": {
|
| 346 |
-
"Average Score": 1.0,
|
| 347 |
-
"Standard Deviation": 0.0,
|
| 348 |
-
"Rank": 1
|
| 349 |
-
},
|
| 350 |
-
"Logical": {
|
| 351 |
-
"Average Score": 1.0,
|
| 352 |
-
"Standard Deviation": 0.0,
|
| 353 |
-
"Rank": 1
|
| 354 |
-
},
|
| 355 |
-
"Social": {
|
| 356 |
-
"Average Score": 0.993974241,
|
| 357 |
-
"Standard Deviation": 0.001996882328,
|
| 358 |
-
"Rank": 2
|
| 359 |
-
}
|
| 360 |
-
}
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"config": {
|
| 364 |
-
"model_name": "o1-preview",
|
| 365 |
-
"organization": "OpenAI",
|
| 366 |
-
"license": "Proprietary",
|
| 367 |
-
"knowledge_cutoff": "2024-01"
|
| 368 |
-
},
|
| 369 |
-
"results": {
|
| 370 |
-
"OVERALL": {
|
| 371 |
-
"Average Score": 0.945884589,
|
| 372 |
-
"Standard Deviation": 0.01059250762,
|
| 373 |
-
"Rank": 3
|
| 374 |
-
},
|
| 375 |
-
"Geometry": {
|
| 376 |
-
"Average Score": "N/A",
|
| 377 |
-
"Standard Deviation": "N/A",
|
| 378 |
-
"Rank": "N/A"
|
| 379 |
-
},
|
| 380 |
-
"Algebra": {
|
| 381 |
-
"Average Score": "N/A",
|
| 382 |
-
"Standard Deviation": "N/A",
|
| 383 |
-
"Rank": "N/A"
|
| 384 |
-
},
|
| 385 |
-
"Probability": {
|
| 386 |
-
"Average Score": 0.964666392,
|
| 387 |
-
"Standard Deviation": 0.003139983398,
|
| 388 |
-
"Rank": 2
|
| 389 |
-
},
|
| 390 |
-
"Logical": {
|
| 391 |
-
"Average Score": 0.987950057,
|
| 392 |
-
"Standard Deviation": 0.004881220327,
|
| 393 |
-
"Rank": 2
|
| 394 |
-
},
|
| 395 |
-
"Social": {
|
| 396 |
-
"Average Score": 1.0,
|
| 397 |
-
"Standard Deviation": 0.0,
|
| 398 |
-
"Rank": 1
|
| 399 |
-
}
|
| 400 |
-
}
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"config": {
|
| 404 |
-
"model_name": "gemini-1.5-flash-001",
|
| 405 |
-
"organization": "Google",
|
| 406 |
-
"license": "Proprietary",
|
| 407 |
-
"knowledge_cutoff": "2024-02"
|
| 408 |
-
},
|
| 409 |
-
"results": {
|
| 410 |
-
"OVERALL": {
|
| 411 |
-
"Average Score": 0.726493401,
|
| 412 |
-
"Standard Deviation": 0.01113913725,
|
| 413 |
-
"Rank": 12
|
| 414 |
-
},
|
| 415 |
-
"Geometry": {
|
| 416 |
-
"Average Score": 0.804144103,
|
| 417 |
-
"Standard Deviation": 0.1327142178,
|
| 418 |
-
"Rank": 8
|
| 419 |
-
},
|
| 420 |
-
"Algebra": {
|
| 421 |
-
"Average Score": 0.731776765,
|
| 422 |
-
"Standard Deviation": 0.02594657111,
|
| 423 |
-
"Rank": 11
|
| 424 |
-
},
|
| 425 |
-
"Probability": {
|
| 426 |
-
"Average Score": 0.614461891,
|
| 427 |
-
"Standard Deviation": 0.04690131826,
|
| 428 |
-
"Rank": 15
|
| 429 |
-
},
|
| 430 |
-
"Logical": {
|
| 431 |
-
"Average Score": 0.630805991,
|
| 432 |
-
"Standard Deviation": 0.04871350612,
|
| 433 |
-
"Rank": 13
|
| 434 |
-
},
|
| 435 |
-
"Social": {
|
| 436 |
-
"Average Score": 0.555933822,
|
| 437 |
-
"Standard Deviation": 0.1029934524,
|
| 438 |
-
"Rank": 16
|
| 439 |
-
}
|
| 440 |
-
}
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"config": {
|
| 444 |
-
"model_name": "gpt4-1106",
|
| 445 |
-
"organization": "OpenAI",
|
| 446 |
-
"license": "Proprietary",
|
| 447 |
-
"knowledge_cutoff": "2024-04"
|
| 448 |
-
},
|
| 449 |
-
"results": {
|
| 450 |
-
"OVERALL": {
|
| 451 |
-
"Average Score": 0.816347784,
|
| 452 |
-
"Standard Deviation": 0.1566815755,
|
| 453 |
-
"Rank": 9
|
| 454 |
-
},
|
| 455 |
-
"Geometry": {
|
| 456 |
-
"Average Score": 0.71843088,
|
| 457 |
-
"Standard Deviation": 0.04778038294,
|
| 458 |
-
"Rank": 13
|
| 459 |
-
},
|
| 460 |
-
"Algebra": {
|
| 461 |
-
"Average Score": 0.712910417,
|
| 462 |
-
"Standard Deviation": 0.02581828898,
|
| 463 |
-
"Rank": 12
|
| 464 |
-
},
|
| 465 |
-
"Probability": {
|
| 466 |
-
"Average Score": 0.623947619,
|
| 467 |
-
"Standard Deviation": 0.03502982933,
|
| 468 |
-
"Rank": 14
|
| 469 |
-
},
|
| 470 |
-
"Logical": {
|
| 471 |
-
"Average Score": 0.637482274,
|
| 472 |
-
"Standard Deviation": 0.04158809888,
|
| 473 |
-
"Rank": 12
|
| 474 |
-
},
|
| 475 |
-
"Social": {
|
| 476 |
-
"Average Score": 0.450609816,
|
| 477 |
-
"Standard Deviation": 0.05208655446,
|
| 478 |
-
"Rank": 23
|
| 479 |
-
}
|
| 480 |
-
}
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"config": {
|
| 484 |
-
"model_name": "gemma-2-27b-it",
|
| 485 |
-
"organization": "Google",
|
| 486 |
-
"license": "Gemma License",
|
| 487 |
-
"knowledge_cutoff": "2024-03"
|
| 488 |
-
},
|
| 489 |
-
"results": {
|
| 490 |
-
"OVERALL": {
|
| 491 |
-
"Average Score": 0.624169623,
|
| 492 |
-
"Standard Deviation": 0.1048365121,
|
| 493 |
-
"Rank": 15
|
| 494 |
-
},
|
| 495 |
-
"Geometry": {
|
| 496 |
-
"Average Score": 0.60112744,
|
| 497 |
-
"Standard Deviation": 0.0469109952,
|
| 498 |
-
"Rank": 19
|
| 499 |
-
},
|
| 500 |
-
"Algebra": {
|
| 501 |
-
"Average Score": 0.687955914,
|
| 502 |
-
"Standard Deviation": 0.01959958192,
|
| 503 |
-
"Rank": 13
|
| 504 |
-
},
|
| 505 |
-
"Probability": {
|
| 506 |
-
"Average Score": 0.589524771,
|
| 507 |
-
"Standard Deviation": 0.03112689325,
|
| 508 |
-
"Rank": 16
|
| 509 |
-
},
|
| 510 |
-
"Logical": {
|
| 511 |
-
"Average Score": 0.614978944,
|
| 512 |
-
"Standard Deviation": 0.05710657859,
|
| 513 |
-
"Rank": 16
|
| 514 |
-
},
|
| 515 |
-
"Social": {
|
| 516 |
-
"Average Score": 0.487844257,
|
| 517 |
-
"Standard Deviation": 0.05857760809,
|
| 518 |
-
"Rank": 20
|
| 519 |
-
}
|
| 520 |
-
}
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"config": {
|
| 524 |
-
"model_name": "claude-3-opus",
|
| 525 |
-
"organization": "Anthropic",
|
| 526 |
-
"license": "Proprietary",
|
| 527 |
-
"knowledge_cutoff": "2024-01"
|
| 528 |
-
},
|
| 529 |
-
"results": {
|
| 530 |
-
"OVERALL": {
|
| 531 |
-
"Average Score": 0.650636271,
|
| 532 |
-
"Standard Deviation": 0.1197773541,
|
| 533 |
-
"Rank": 14
|
| 534 |
-
},
|
| 535 |
-
"Geometry": {
|
| 536 |
-
"Average Score": 0.7215743,
|
| 537 |
-
"Standard Deviation": 0.04712598358,
|
| 538 |
-
"Rank": 12
|
| 539 |
-
},
|
| 540 |
-
"Algebra": {
|
| 541 |
-
"Average Score": 0.68777327,
|
| 542 |
-
"Standard Deviation": 0.02382683713,
|
| 543 |
-
"Rank": 14
|
| 544 |
-
},
|
| 545 |
-
"Probability": {
|
| 546 |
-
"Average Score": 0.626471421,
|
| 547 |
-
"Standard Deviation": 0.02911817976,
|
| 548 |
-
"Rank": 13
|
| 549 |
-
},
|
| 550 |
-
"Logical": {
|
| 551 |
-
"Average Score": 0.692346381,
|
| 552 |
-
"Standard Deviation": 0.03617185198,
|
| 553 |
-
"Rank": 10
|
| 554 |
-
},
|
| 555 |
-
"Social": {
|
| 556 |
-
"Average Score": 0.663410854,
|
| 557 |
-
"Standard Deviation": 0.09540220876,
|
| 558 |
-
"Rank": 10
|
| 559 |
-
}
|
| 560 |
-
}
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"config": {
|
| 564 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 565 |
-
"organization": "Google",
|
| 566 |
-
"license": "Gemma License",
|
| 567 |
-
"knowledge_cutoff": "2024-02"
|
| 568 |
-
},
|
| 569 |
-
"results": {
|
| 570 |
-
"OVERALL": {
|
| 571 |
-
"Average Score": "N/A",
|
| 572 |
-
"Standard Deviation": "N/A",
|
| 573 |
-
"Rank": "N/A"
|
| 574 |
-
},
|
| 575 |
-
"Geometry": {
|
| 576 |
-
"Average Score": 0.582787508,
|
| 577 |
-
"Standard Deviation": 0.03965204074,
|
| 578 |
-
"Rank": 20
|
| 579 |
-
},
|
| 580 |
-
"Algebra": {
|
| 581 |
-
"Average Score": 0.658648133,
|
| 582 |
-
"Standard Deviation": 0.02565919856,
|
| 583 |
-
"Rank": 15
|
| 584 |
-
},
|
| 585 |
-
"Probability": {
|
| 586 |
-
"Average Score": 0.547861265,
|
| 587 |
-
"Standard Deviation": 0.02885209131,
|
| 588 |
-
"Rank": 19
|
| 589 |
-
},
|
| 590 |
-
"Logical": {
|
| 591 |
-
"Average Score": 0.540720893,
|
| 592 |
-
"Standard Deviation": 0.01970134508,
|
| 593 |
-
"Rank": 20
|
| 594 |
-
},
|
| 595 |
-
"Social": {
|
| 596 |
-
"Average Score": 0.635266187,
|
| 597 |
-
"Standard Deviation": 0.03620021751,
|
| 598 |
-
"Rank": 13
|
| 599 |
-
}
|
| 600 |
-
}
|
| 601 |
-
},
|
| 602 |
-
{
|
| 603 |
-
"config": {
|
| 604 |
-
"model_name": "qwen1.5-72b-chat",
|
| 605 |
-
"organization": "Alibaba",
|
| 606 |
-
"license": "Qianwen LICENSE",
|
| 607 |
-
"knowledge_cutoff": "2024-03"
|
| 608 |
-
},
|
| 609 |
-
"results": {
|
| 610 |
-
"OVERALL": {
|
| 611 |
-
"Average Score": 0.519549796,
|
| 612 |
-
"Standard Deviation": 0.00903634343,
|
| 613 |
-
"Rank": 18
|
| 614 |
-
},
|
| 615 |
-
"Geometry": {
|
| 616 |
-
"Average Score": 0.543139301,
|
| 617 |
-
"Standard Deviation": 0.03425202326,
|
| 618 |
-
"Rank": 24
|
| 619 |
-
},
|
| 620 |
-
"Algebra": {
|
| 621 |
-
"Average Score": 0.635228729,
|
| 622 |
-
"Standard Deviation": 0.01944043425,
|
| 623 |
-
"Rank": 16
|
| 624 |
-
},
|
| 625 |
-
"Probability": {
|
| 626 |
-
"Average Score": 0.486948658,
|
| 627 |
-
"Standard Deviation": 0.06064655315,
|
| 628 |
-
"Rank": 23
|
| 629 |
-
},
|
| 630 |
-
"Logical": {
|
| 631 |
-
"Average Score": 0.284069394,
|
| 632 |
-
"Standard Deviation": 0.02686608506,
|
| 633 |
-
"Rank": 33
|
| 634 |
-
},
|
| 635 |
-
"Social": {
|
| 636 |
-
"Average Score": 0.415007627,
|
| 637 |
-
"Standard Deviation": 0.03920053159,
|
| 638 |
-
"Rank": 24
|
| 639 |
-
}
|
| 640 |
-
}
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"config": {
|
| 644 |
-
"model_name": "qwen1.5-32b-chat",
|
| 645 |
-
"organization": "Alibaba",
|
| 646 |
-
"license": "Qianwen LICENSE",
|
| 647 |
-
"knowledge_cutoff": "2024-03"
|
| 648 |
-
},
|
| 649 |
-
"results": {
|
| 650 |
-
"OVERALL": {
|
| 651 |
-
"Average Score": 0.393789407,
|
| 652 |
-
"Standard Deviation": 0.05413770095,
|
| 653 |
-
"Rank": 29
|
| 654 |
-
},
|
| 655 |
-
"Geometry": {
|
| 656 |
-
"Average Score": 0.51086835,
|
| 657 |
-
"Standard Deviation": 0.04052471998,
|
| 658 |
-
"Rank": 27
|
| 659 |
-
},
|
| 660 |
-
"Algebra": {
|
| 661 |
-
"Average Score": 0.609003168,
|
| 662 |
-
"Standard Deviation": 0.04874143541,
|
| 663 |
-
"Rank": 17
|
| 664 |
-
},
|
| 665 |
-
"Probability": {
|
| 666 |
-
"Average Score": 0.476300002,
|
| 667 |
-
"Standard Deviation": 0.05322403912,
|
| 668 |
-
"Rank": 24
|
| 669 |
-
},
|
| 670 |
-
"Logical": {
|
| 671 |
-
"Average Score": 0.331781014,
|
| 672 |
-
"Standard Deviation": 0.004938997686,
|
| 673 |
-
"Rank": 30
|
| 674 |
-
},
|
| 675 |
-
"Social": {
|
| 676 |
-
"Average Score": 0.380987334,
|
| 677 |
-
"Standard Deviation": 0.03762251776,
|
| 678 |
-
"Rank": 26
|
| 679 |
-
}
|
| 680 |
-
}
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"config": {
|
| 684 |
-
"model_name": "google-gemma-2-9b-it",
|
| 685 |
-
"organization": "Google",
|
| 686 |
-
"license": "Proprietary",
|
| 687 |
-
"knowledge_cutoff": "2024-01"
|
| 688 |
-
},
|
| 689 |
-
"results": {
|
| 690 |
-
"OVERALL": {
|
| 691 |
-
"Average Score": 0.489663449,
|
| 692 |
-
"Standard Deviation": 0.002595702019,
|
| 693 |
-
"Rank": 21
|
| 694 |
-
},
|
| 695 |
-
"Geometry": {
|
| 696 |
-
"Average Score": 0.575371308,
|
| 697 |
-
"Standard Deviation": 0.03556220251,
|
| 698 |
-
"Rank": 22
|
| 699 |
-
},
|
| 700 |
-
"Algebra": {
|
| 701 |
-
"Average Score": 0.597045661,
|
| 702 |
-
"Standard Deviation": 0.0313828123,
|
| 703 |
-
"Rank": 18
|
| 704 |
-
},
|
| 705 |
-
"Probability": {
|
| 706 |
-
"Average Score": 0.589221807,
|
| 707 |
-
"Standard Deviation": 0.03110811656,
|
| 708 |
-
"Rank": 18
|
| 709 |
-
},
|
| 710 |
-
"Logical": {
|
| 711 |
-
"Average Score": 0.587579897,
|
| 712 |
-
"Standard Deviation": 0.05512716783,
|
| 713 |
-
"Rank": 18
|
| 714 |
-
},
|
| 715 |
-
"Social": {
|
| 716 |
-
"Average Score": 0.768337958,
|
| 717 |
-
"Standard Deviation": 0.04078610476,
|
| 718 |
-
"Rank": 6
|
| 719 |
-
}
|
| 720 |
-
}
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"config": {
|
| 724 |
-
"model_name": "yi-1.5-34b-chat",
|
| 725 |
-
"organization": "01 AI",
|
| 726 |
-
"license": "Proprietary",
|
| 727 |
-
"knowledge_cutoff": "2024-01"
|
| 728 |
-
},
|
| 729 |
-
"results": {
|
| 730 |
-
"OVERALL": {
|
| 731 |
-
"Average Score": 0.607812897,
|
| 732 |
-
"Standard Deviation": 0.1440881293,
|
| 733 |
-
"Rank": 16
|
| 734 |
-
},
|
| 735 |
-
"Geometry": {
|
| 736 |
-
"Average Score": 0.566666724,
|
| 737 |
-
"Standard Deviation": 0.04001381658,
|
| 738 |
-
"Rank": 23
|
| 739 |
-
},
|
| 740 |
-
"Algebra": {
|
| 741 |
-
"Average Score": 0.590997292,
|
| 742 |
-
"Standard Deviation": 0.03594087315,
|
| 743 |
-
"Rank": 19
|
| 744 |
-
},
|
| 745 |
-
"Probability": {
|
| 746 |
-
"Average Score": 0.589524589,
|
| 747 |
-
"Standard Deviation": 0.03112618772,
|
| 748 |
-
"Rank": 17
|
| 749 |
-
},
|
| 750 |
-
"Logical": {
|
| 751 |
-
"Average Score": 0.574105508,
|
| 752 |
-
"Standard Deviation": 0.03441737941,
|
| 753 |
-
"Rank": 19
|
| 754 |
-
},
|
| 755 |
-
"Social": {
|
| 756 |
-
"Average Score": 0.516980832,
|
| 757 |
-
"Standard Deviation": 0.03369347985,
|
| 758 |
-
"Rank": 19
|
| 759 |
-
}
|
| 760 |
-
}
|
| 761 |
-
},
|
| 762 |
-
{
|
| 763 |
-
"config": {
|
| 764 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 765 |
-
"organization": "Meta",
|
| 766 |
-
"license": "Llama 3.1 Community",
|
| 767 |
-
"knowledge_cutoff": "2024-02"
|
| 768 |
-
},
|
| 769 |
-
"results": {
|
| 770 |
-
"OVERALL": {
|
| 771 |
-
"Average Score": 0.505936324,
|
| 772 |
-
"Standard Deviation": 0.05286756493,
|
| 773 |
-
"Rank": 19
|
| 774 |
-
},
|
| 775 |
-
"Geometry": {
|
| 776 |
-
"Average Score": 0.522442162,
|
| 777 |
-
"Standard Deviation": 0.03908236317,
|
| 778 |
-
"Rank": 25
|
| 779 |
-
},
|
| 780 |
-
"Algebra": {
|
| 781 |
-
"Average Score": 0.582702645,
|
| 782 |
-
"Standard Deviation": 0.05002277711,
|
| 783 |
-
"Rank": 20
|
| 784 |
-
},
|
| 785 |
-
"Probability": {
|
| 786 |
-
"Average Score": 0.495001149,
|
| 787 |
-
"Standard Deviation": 0.05244587037,
|
| 788 |
-
"Rank": 22
|
| 789 |
-
},
|
| 790 |
-
"Logical": {
|
| 791 |
-
"Average Score": 0.443030561,
|
| 792 |
-
"Standard Deviation": 0.01343820628,
|
| 793 |
-
"Rank": 25
|
| 794 |
-
},
|
| 795 |
-
"Social": {
|
| 796 |
-
"Average Score": 0.329195941,
|
| 797 |
-
"Standard Deviation": 0.03925019528,
|
| 798 |
-
"Rank": 30
|
| 799 |
-
}
|
| 800 |
-
}
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"config": {
|
| 804 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 805 |
-
"organization": "OpenAI",
|
| 806 |
-
"license": "Proprietary",
|
| 807 |
-
"knowledge_cutoff": "2023-12"
|
| 808 |
-
},
|
| 809 |
-
"results": {
|
| 810 |
-
"OVERALL": {
|
| 811 |
-
"Average Score": 0.313398088,
|
| 812 |
-
"Standard Deviation": 0.09322528606,
|
| 813 |
-
"Rank": 40
|
| 814 |
-
},
|
| 815 |
-
"Geometry": {
|
| 816 |
-
"Average Score": 0.678714519,
|
| 817 |
-
"Standard Deviation": 0.05926546762,
|
| 818 |
-
"Rank": 14
|
| 819 |
-
},
|
| 820 |
-
"Algebra": {
|
| 821 |
-
"Average Score": 0.569296173,
|
| 822 |
-
"Standard Deviation": 0.05277281097,
|
| 823 |
-
"Rank": 21
|
| 824 |
-
},
|
| 825 |
-
"Probability": {
|
| 826 |
-
"Average Score": 0.448460767,
|
| 827 |
-
"Standard Deviation": 0.05768095196,
|
| 828 |
-
"Rank": 26
|
| 829 |
-
},
|
| 830 |
-
"Logical": {
|
| 831 |
-
"Average Score": 0.148521348,
|
| 832 |
-
"Standard Deviation": 0.04033712907,
|
| 833 |
-
"Rank": 45
|
| 834 |
-
},
|
| 835 |
-
"Social": {
|
| 836 |
-
"Average Score": 0.235071541,
|
| 837 |
-
"Standard Deviation": 0.02632892457,
|
| 838 |
-
"Rank": 39
|
| 839 |
-
}
|
| 840 |
-
}
|
| 841 |
-
},
|
| 842 |
-
{
|
| 843 |
-
"config": {
|
| 844 |
-
"model_name": "llama-3-70b-instruct",
|
| 845 |
-
"organization": "Meta",
|
| 846 |
-
"license": "Llama 3 Community",
|
| 847 |
-
"knowledge_cutoff": "2024-03"
|
| 848 |
-
},
|
| 849 |
-
"results": {
|
| 850 |
-
"OVERALL": {
|
| 851 |
-
"Average Score": 0.456689885,
|
| 852 |
-
"Standard Deviation": 0.01385989995,
|
| 853 |
-
"Rank": 23
|
| 854 |
-
},
|
| 855 |
-
"Geometry": {
|
| 856 |
-
"Average Score": 0.516865529,
|
| 857 |
-
"Standard Deviation": 0.03858112564,
|
| 858 |
-
"Rank": 26
|
| 859 |
-
},
|
| 860 |
-
"Algebra": {
|
| 861 |
-
"Average Score": 0.566756531,
|
| 862 |
-
"Standard Deviation": 0.03369826926,
|
| 863 |
-
"Rank": 22
|
| 864 |
-
},
|
| 865 |
-
"Probability": {
|
| 866 |
-
"Average Score": 0.513857306,
|
| 867 |
-
"Standard Deviation": 0.05453699062,
|
| 868 |
-
"Rank": 21
|
| 869 |
-
},
|
| 870 |
-
"Logical": {
|
| 871 |
-
"Average Score": 0.713796415,
|
| 872 |
-
"Standard Deviation": 0.02031215107,
|
| 873 |
-
"Rank": 9
|
| 874 |
-
},
|
| 875 |
-
"Social": {
|
| 876 |
-
"Average Score": 0.45872939,
|
| 877 |
-
"Standard Deviation": 0.05347039576,
|
| 878 |
-
"Rank": 22
|
| 879 |
-
}
|
| 880 |
-
}
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"config": {
|
| 884 |
-
"model_name": "claude-3-sonnet",
|
| 885 |
-
"organization": "Anthropic",
|
| 886 |
-
"license": "Proprietary",
|
| 887 |
-
"knowledge_cutoff": "2024-02"
|
| 888 |
-
},
|
| 889 |
-
"results": {
|
| 890 |
-
"OVERALL": {
|
| 891 |
-
"Average Score": 0.520010833,
|
| 892 |
-
"Standard Deviation": 0.005030563799,
|
| 893 |
-
"Rank": 17
|
| 894 |
-
},
|
| 895 |
-
"Geometry": {
|
| 896 |
-
"Average Score": 0.675613638,
|
| 897 |
-
"Standard Deviation": 0.05275594408,
|
| 898 |
-
"Rank": 15
|
| 899 |
-
},
|
| 900 |
-
"Algebra": {
|
| 901 |
-
"Average Score": 0.552025728,
|
| 902 |
-
"Standard Deviation": 0.04122192409,
|
| 903 |
-
"Rank": 23
|
| 904 |
-
},
|
| 905 |
-
"Probability": {
|
| 906 |
-
"Average Score": 0.516192848,
|
| 907 |
-
"Standard Deviation": 0.04152293217,
|
| 908 |
-
"Rank": 20
|
| 909 |
-
},
|
| 910 |
-
"Logical": {
|
| 911 |
-
"Average Score": 0.588545747,
|
| 912 |
-
"Standard Deviation": 0.06068211943,
|
| 913 |
-
"Rank": 17
|
| 914 |
-
},
|
| 915 |
-
"Social": {
|
| 916 |
-
"Average Score": 0.570437582,
|
| 917 |
-
"Standard Deviation": 0.08607040862,
|
| 918 |
-
"Rank": 15
|
| 919 |
-
}
|
| 920 |
-
}
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"config": {
|
| 924 |
-
"model_name": "qwen1.5-14b-chat",
|
| 925 |
-
"organization": "Alibaba",
|
| 926 |
-
"license": "Qianwen LICENSE",
|
| 927 |
-
"knowledge_cutoff": "2024-01"
|
| 928 |
-
},
|
| 929 |
-
"results": {
|
| 930 |
-
"OVERALL": {
|
| 931 |
-
"Average Score": 0.415328996,
|
| 932 |
-
"Standard Deviation": 0.0743938717,
|
| 933 |
-
"Rank": 28
|
| 934 |
-
},
|
| 935 |
-
"Geometry": {
|
| 936 |
-
"Average Score": 0.452504016,
|
| 937 |
-
"Standard Deviation": 0.04225594393,
|
| 938 |
-
"Rank": 28
|
| 939 |
-
},
|
| 940 |
-
"Algebra": {
|
| 941 |
-
"Average Score": 0.538655725,
|
| 942 |
-
"Standard Deviation": 0.03721542594,
|
| 943 |
-
"Rank": 24
|
| 944 |
-
},
|
| 945 |
-
"Probability": {
|
| 946 |
-
"Average Score": 0.397185975,
|
| 947 |
-
"Standard Deviation": 0.05607695946,
|
| 948 |
-
"Rank": 30
|
| 949 |
-
},
|
| 950 |
-
"Logical": {
|
| 951 |
-
"Average Score": 0.264573129,
|
| 952 |
-
"Standard Deviation": 0.03936133174,
|
| 953 |
-
"Rank": 35
|
| 954 |
-
},
|
| 955 |
-
"Social": {
|
| 956 |
-
"Average Score": 0.287370142,
|
| 957 |
-
"Standard Deviation": 0.04264085315,
|
| 958 |
-
"Rank": 32
|
| 959 |
-
}
|
| 960 |
-
}
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"config": {
|
| 964 |
-
"model_name": "claude-3-haiku",
|
| 965 |
-
"organization": "Anthropic",
|
| 966 |
-
"license": "Proprietary",
|
| 967 |
-
"knowledge_cutoff": "2024-01"
|
| 968 |
-
},
|
| 969 |
-
"results": {
|
| 970 |
-
"OVERALL": {
|
| 971 |
-
"Average Score": 0.453901163,
|
| 972 |
-
"Standard Deviation": 0.003604084261,
|
| 973 |
-
"Rank": 24
|
| 974 |
-
},
|
| 975 |
-
"Geometry": {
|
| 976 |
-
"Average Score": 0.607993912,
|
| 977 |
-
"Standard Deviation": 0.05793460748,
|
| 978 |
-
"Rank": 17
|
| 979 |
-
},
|
| 980 |
-
"Algebra": {
|
| 981 |
-
"Average Score": 0.520054055,
|
| 982 |
-
"Standard Deviation": 0.03333544511,
|
| 983 |
-
"Rank": 25
|
| 984 |
-
},
|
| 985 |
-
"Probability": {
|
| 986 |
-
"Average Score": 0.474460688,
|
| 987 |
-
"Standard Deviation": 0.0446501933,
|
| 988 |
-
"Rank": 25
|
| 989 |
-
},
|
| 990 |
-
"Logical": {
|
| 991 |
-
"Average Score": 0.512815976,
|
| 992 |
-
"Standard Deviation": 0.0163264281,
|
| 993 |
-
"Rank": 21
|
| 994 |
-
},
|
| 995 |
-
"Social": {
|
| 996 |
-
"Average Score": 0.551083976,
|
| 997 |
-
"Standard Deviation": 0.05374722539,
|
| 998 |
-
"Rank": 17
|
| 999 |
-
}
|
| 1000 |
-
}
|
| 1001 |
-
},
|
| 1002 |
-
{
|
| 1003 |
-
"config": {
|
| 1004 |
-
"model_name": "claude-2.1",
|
| 1005 |
-
"organization": "Anthropic",
|
| 1006 |
-
"license": "Proprietary",
|
| 1007 |
-
"knowledge_cutoff": "2023-12"
|
| 1008 |
-
},
|
| 1009 |
-
"results": {
|
| 1010 |
-
"OVERALL": {
|
| 1011 |
-
"Average Score": 0.35814708,
|
| 1012 |
-
"Standard Deviation": 0.09168134168,
|
| 1013 |
-
"Rank": 36
|
| 1014 |
-
},
|
| 1015 |
-
"Geometry": {
|
| 1016 |
-
"Average Score": 0.62752395,
|
| 1017 |
-
"Standard Deviation": 0.07232659398,
|
| 1018 |
-
"Rank": 16
|
| 1019 |
-
},
|
| 1020 |
-
"Algebra": {
|
| 1021 |
-
"Average Score": 0.508849609,
|
| 1022 |
-
"Standard Deviation": 0.0346897465,
|
| 1023 |
-
"Rank": 26
|
| 1024 |
-
},
|
| 1025 |
-
"Probability": {
|
| 1026 |
-
"Average Score": 0.41477086,
|
| 1027 |
-
"Standard Deviation": 0.05964060239,
|
| 1028 |
-
"Rank": 29
|
| 1029 |
-
},
|
| 1030 |
-
"Logical": {
|
| 1031 |
-
"Average Score": 0.482923674,
|
| 1032 |
-
"Standard Deviation": 0.01989147048,
|
| 1033 |
-
"Rank": 22
|
| 1034 |
-
},
|
| 1035 |
-
"Social": {
|
| 1036 |
-
"Average Score": 0.333804568,
|
| 1037 |
-
"Standard Deviation": 0.03775548253,
|
| 1038 |
-
"Rank": 29
|
| 1039 |
-
}
|
| 1040 |
-
}
|
| 1041 |
-
},
|
| 1042 |
-
{
|
| 1043 |
-
"config": {
|
| 1044 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 1045 |
-
"organization": "Mistral",
|
| 1046 |
-
"license": "Apache 2.0",
|
| 1047 |
-
"knowledge_cutoff": "2023-12"
|
| 1048 |
-
},
|
| 1049 |
-
"results": {
|
| 1050 |
-
"OVERALL": {
|
| 1051 |
-
"Average Score": 0.382659161,
|
| 1052 |
-
"Standard Deviation": 0.07594496929,
|
| 1053 |
-
"Rank": 31
|
| 1054 |
-
},
|
| 1055 |
-
"Geometry": {
|
| 1056 |
-
"Average Score": 0.432216097,
|
| 1057 |
-
"Standard Deviation": 0.04747949254,
|
| 1058 |
-
"Rank": 31
|
| 1059 |
-
},
|
| 1060 |
-
"Algebra": {
|
| 1061 |
-
"Average Score": 0.478314888,
|
| 1062 |
-
"Standard Deviation": 0.01998797419,
|
| 1063 |
-
"Rank": 27
|
| 1064 |
-
},
|
| 1065 |
-
"Probability": {
|
| 1066 |
-
"Average Score": 0.427144725,
|
| 1067 |
-
"Standard Deviation": 0.0590923329,
|
| 1068 |
-
"Rank": 28
|
| 1069 |
-
},
|
| 1070 |
-
"Logical": {
|
| 1071 |
-
"Average Score": 0.340041983,
|
| 1072 |
-
"Standard Deviation": 0.008397574592,
|
| 1073 |
-
"Rank": 28
|
| 1074 |
-
},
|
| 1075 |
-
"Social": {
|
| 1076 |
-
"Average Score": 0.251949622,
|
| 1077 |
-
"Standard Deviation": 0.03346674405,
|
| 1078 |
-
"Rank": 37
|
| 1079 |
-
}
|
| 1080 |
-
}
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"config": {
|
| 1084 |
-
"model_name": "claude-2.0",
|
| 1085 |
-
"organization": "Anthropic",
|
| 1086 |
-
"license": "Proprietary",
|
| 1087 |
-
"knowledge_cutoff": "2023-10"
|
| 1088 |
-
},
|
| 1089 |
-
"results": {
|
| 1090 |
-
"OVERALL": {
|
| 1091 |
-
"Average Score": 0.322718057,
|
| 1092 |
-
"Standard Deviation": 0.08369883584,
|
| 1093 |
-
"Rank": 38
|
| 1094 |
-
},
|
| 1095 |
-
"Geometry": {
|
| 1096 |
-
"Average Score": 0.604141967,
|
| 1097 |
-
"Standard Deviation": 0.05116441826,
|
| 1098 |
-
"Rank": 18
|
| 1099 |
-
},
|
| 1100 |
-
"Algebra": {
|
| 1101 |
-
"Average Score": 0.474350734,
|
| 1102 |
-
"Standard Deviation": 0.01510393066,
|
| 1103 |
-
"Rank": 28
|
| 1104 |
-
},
|
| 1105 |
-
"Probability": {
|
| 1106 |
-
"Average Score": 0.437950412,
|
| 1107 |
-
"Standard Deviation": 0.05985594317,
|
| 1108 |
-
"Rank": 27
|
| 1109 |
-
},
|
| 1110 |
-
"Logical": {
|
| 1111 |
-
"Average Score": 0.445620646,
|
| 1112 |
-
"Standard Deviation": 0.01812614805,
|
| 1113 |
-
"Rank": 24
|
| 1114 |
-
},
|
| 1115 |
-
"Social": {
|
| 1116 |
-
"Average Score": 0.469422836,
|
| 1117 |
-
"Standard Deviation": 0.05999901796,
|
| 1118 |
-
"Rank": 21
|
| 1119 |
-
}
|
| 1120 |
-
}
|
| 1121 |
-
},
|
| 1122 |
-
{
|
| 1123 |
-
"config": {
|
| 1124 |
-
"model_name": "starling-lm-7b-beta",
|
| 1125 |
-
"organization": "Nexusflow",
|
| 1126 |
-
"license": "Apache-2.0",
|
| 1127 |
-
"knowledge_cutoff": "2024-01"
|
| 1128 |
-
},
|
| 1129 |
-
"results": {
|
| 1130 |
-
"OVERALL": {
|
| 1131 |
-
"Average Score": 0.479391856,
|
| 1132 |
-
"Standard Deviation": 0.04199990887,
|
| 1133 |
-
"Rank": 22
|
| 1134 |
-
},
|
| 1135 |
-
"Geometry": {
|
| 1136 |
-
"Average Score": 0.446654388,
|
| 1137 |
-
"Standard Deviation": 0.05637864999,
|
| 1138 |
-
"Rank": 30
|
| 1139 |
-
},
|
| 1140 |
-
"Algebra": {
|
| 1141 |
-
"Average Score": 0.473952749,
|
| 1142 |
-
"Standard Deviation": 0.01584301288,
|
| 1143 |
-
"Rank": 29
|
| 1144 |
-
},
|
| 1145 |
-
"Probability": {
|
| 1146 |
-
"Average Score": 0.395197837,
|
| 1147 |
-
"Standard Deviation": 0.05814798892,
|
| 1148 |
-
"Rank": 31
|
| 1149 |
-
},
|
| 1150 |
-
"Logical": {
|
| 1151 |
-
"Average Score": 0.39927199,
|
| 1152 |
-
"Standard Deviation": 0.02125277518,
|
| 1153 |
-
"Rank": 26
|
| 1154 |
-
},
|
| 1155 |
-
"Social": {
|
| 1156 |
-
"Average Score": 0.380021662,
|
| 1157 |
-
"Standard Deviation": 0.04622452748,
|
| 1158 |
-
"Rank": 27
|
| 1159 |
-
}
|
| 1160 |
-
}
|
| 1161 |
-
},
|
| 1162 |
-
{
|
| 1163 |
-
"config": {
|
| 1164 |
-
"model_name": "gemini-1.0-pro-001",
|
| 1165 |
-
"organization": "Google",
|
| 1166 |
-
"license": "Proprietary",
|
| 1167 |
-
"knowledge_cutoff": "2023-11"
|
| 1168 |
-
},
|
| 1169 |
-
"results": {
|
| 1170 |
-
"OVERALL": {
|
| 1171 |
-
"Average Score": 0.449040654,
|
| 1172 |
-
"Standard Deviation": 0.0450610177,
|
| 1173 |
-
"Rank": 25
|
| 1174 |
-
},
|
| 1175 |
-
"Geometry": {
|
| 1176 |
-
"Average Score": 0.578347959,
|
| 1177 |
-
"Standard Deviation": 0.04242873607,
|
| 1178 |
-
"Rank": 21
|
| 1179 |
-
},
|
| 1180 |
-
"Algebra": {
|
| 1181 |
-
"Average Score": 0.462417786,
|
| 1182 |
-
"Standard Deviation": 0.01668313635,
|
| 1183 |
-
"Rank": 30
|
| 1184 |
-
},
|
| 1185 |
-
"Probability": {
|
| 1186 |
-
"Average Score": 0.289836324,
|
| 1187 |
-
"Standard Deviation": 0.05739831115,
|
| 1188 |
-
"Rank": 39
|
| 1189 |
-
},
|
| 1190 |
-
"Logical": {
|
| 1191 |
-
"Average Score": 0.191140355,
|
| 1192 |
-
"Standard Deviation": 0.03394652499,
|
| 1193 |
-
"Rank": 41
|
| 1194 |
-
},
|
| 1195 |
-
"Social": {
|
| 1196 |
-
"Average Score": 0.130790863,
|
| 1197 |
-
"Standard Deviation": 0.02800188173,
|
| 1198 |
-
"Rank": 47
|
| 1199 |
-
}
|
| 1200 |
-
}
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"config": {
|
| 1204 |
-
"model_name": "openchat-3.5-0106",
|
| 1205 |
-
"organization": "OpenChat",
|
| 1206 |
-
"license": "Apache-2.0",
|
| 1207 |
-
"knowledge_cutoff": "2024-01"
|
| 1208 |
-
},
|
| 1209 |
-
"results": {
|
| 1210 |
-
"OVERALL": {
|
| 1211 |
-
"Average Score": 0.363929888,
|
| 1212 |
-
"Standard Deviation": 0.08602347145,
|
| 1213 |
-
"Rank": 34
|
| 1214 |
-
},
|
| 1215 |
-
"Geometry": {
|
| 1216 |
-
"Average Score": 0.38715246,
|
| 1217 |
-
"Standard Deviation": 0.03701851946,
|
| 1218 |
-
"Rank": 34
|
| 1219 |
-
},
|
| 1220 |
-
"Algebra": {
|
| 1221 |
-
"Average Score": 0.441233712,
|
| 1222 |
-
"Standard Deviation": 0.01135753754,
|
| 1223 |
-
"Rank": 31
|
| 1224 |
-
},
|
| 1225 |
-
"Probability": {
|
| 1226 |
-
"Average Score": 0.38802618,
|
| 1227 |
-
"Standard Deviation": 0.05663879714,
|
| 1228 |
-
"Rank": 32
|
| 1229 |
-
},
|
| 1230 |
-
"Logical": {
|
| 1231 |
-
"Average Score": 0.336754383,
|
| 1232 |
-
"Standard Deviation": 0.01608478079,
|
| 1233 |
-
"Rank": 29
|
| 1234 |
-
},
|
| 1235 |
-
"Social": {
|
| 1236 |
-
"Average Score": 0.250891608,
|
| 1237 |
-
"Standard Deviation": 0.03253769914,
|
| 1238 |
-
"Rank": 38
|
| 1239 |
-
}
|
| 1240 |
-
}
|
| 1241 |
-
},
|
| 1242 |
-
{
|
| 1243 |
-
"config": {
|
| 1244 |
-
"model_name": "openchat-3.5",
|
| 1245 |
-
"organization": "OpenChat",
|
| 1246 |
-
"license": "Apache-2.0",
|
| 1247 |
-
"knowledge_cutoff": "2023-12"
|
| 1248 |
-
},
|
| 1249 |
-
"results": {
|
| 1250 |
-
"OVERALL": {
|
| 1251 |
-
"Average Score": 0.361341296,
|
| 1252 |
-
"Standard Deviation": 0.09034869493,
|
| 1253 |
-
"Rank": 35
|
| 1254 |
-
},
|
| 1255 |
-
"Geometry": {
|
| 1256 |
-
"Average Score": 0.401699069,
|
| 1257 |
-
"Standard Deviation": 0.03410726557,
|
| 1258 |
-
"Rank": 32
|
| 1259 |
-
},
|
| 1260 |
-
"Algebra": {
|
| 1261 |
-
"Average Score": 0.414095336,
|
| 1262 |
-
"Standard Deviation": 0.01881964261,
|
| 1263 |
-
"Rank": 33
|
| 1264 |
-
},
|
| 1265 |
-
"Probability": {
|
| 1266 |
-
"Average Score": 0.349601002,
|
| 1267 |
-
"Standard Deviation": 0.05077455539,
|
| 1268 |
-
"Rank": 34
|
| 1269 |
-
},
|
| 1270 |
-
"Logical": {
|
| 1271 |
-
"Average Score": 0.331069242,
|
| 1272 |
-
"Standard Deviation": 0.02180827173,
|
| 1273 |
-
"Rank": 31
|
| 1274 |
-
},
|
| 1275 |
-
"Social": {
|
| 1276 |
-
"Average Score": 0.319991655,
|
| 1277 |
-
"Standard Deviation": 0.04502478724,
|
| 1278 |
-
"Rank": 31
|
| 1279 |
-
}
|
| 1280 |
-
}
|
| 1281 |
-
},
|
| 1282 |
-
{
|
| 1283 |
-
"config": {
|
| 1284 |
-
"model_name": "command-r-(08-2024)",
|
| 1285 |
-
"organization": "Cohere",
|
| 1286 |
-
"license": "CC-BY-NC-4.0",
|
| 1287 |
-
"knowledge_cutoff": "2024-08"
|
| 1288 |
-
},
|
| 1289 |
-
"results": {
|
| 1290 |
-
"OVERALL": {
|
| 1291 |
-
"Average Score": 0.427605298,
|
| 1292 |
-
"Standard Deviation": 0.01747449163,
|
| 1293 |
-
"Rank": 26
|
| 1294 |
-
},
|
| 1295 |
-
"Geometry": {
|
| 1296 |
-
"Average Score": 0.448300727,
|
| 1297 |
-
"Standard Deviation": 0.04996362328,
|
| 1298 |
-
"Rank": 29
|
| 1299 |
-
},
|
| 1300 |
-
"Algebra": {
|
| 1301 |
-
"Average Score": 0.417519167,
|
| 1302 |
-
"Standard Deviation": 0.01822196902,
|
| 1303 |
-
"Rank": 32
|
| 1304 |
-
},
|
| 1305 |
-
"Probability": {
|
| 1306 |
-
"Average Score": 0.366336281,
|
| 1307 |
-
"Standard Deviation": 0.04716826942,
|
| 1308 |
-
"Rank": 33
|
| 1309 |
-
},
|
| 1310 |
-
"Logical": {
|
| 1311 |
-
"Average Score": 0.214657906,
|
| 1312 |
-
"Standard Deviation": 0.03003579835,
|
| 1313 |
-
"Rank": 38
|
| 1314 |
-
},
|
| 1315 |
-
"Social": {
|
| 1316 |
-
"Average Score": 0.276088379,
|
| 1317 |
-
"Standard Deviation": 0.03295234688,
|
| 1318 |
-
"Rank": 34
|
| 1319 |
-
}
|
| 1320 |
-
}
|
| 1321 |
-
},
|
| 1322 |
-
{
|
| 1323 |
-
"config": {
|
| 1324 |
-
"model_name": "gemma-1.1-7b-it",
|
| 1325 |
-
"organization": "Google",
|
| 1326 |
-
"license": "Gemma License",
|
| 1327 |
-
"knowledge_cutoff": "2023-11"
|
| 1328 |
-
},
|
| 1329 |
-
"results": {
|
| 1330 |
-
"OVERALL": {
|
| 1331 |
-
"Average Score": 0.339506922,
|
| 1332 |
-
"Standard Deviation": 0.1066279108,
|
| 1333 |
-
"Rank": 37
|
| 1334 |
-
},
|
| 1335 |
-
"Geometry": {
|
| 1336 |
-
"Average Score": 0.324170977,
|
| 1337 |
-
"Standard Deviation": 0.04668553765,
|
| 1338 |
-
"Rank": 37
|
| 1339 |
-
},
|
| 1340 |
-
"Algebra": {
|
| 1341 |
-
"Average Score": 0.398684697,
|
| 1342 |
-
"Standard Deviation": 0.01982398259,
|
| 1343 |
-
"Rank": 34
|
| 1344 |
-
},
|
| 1345 |
-
"Probability": {
|
| 1346 |
-
"Average Score": 0.293253175,
|
| 1347 |
-
"Standard Deviation": 0.05126192191,
|
| 1348 |
-
"Rank": 38
|
| 1349 |
-
},
|
| 1350 |
-
"Logical": {
|
| 1351 |
-
"Average Score": 0.317750796,
|
| 1352 |
-
"Standard Deviation": 0.01101933543,
|
| 1353 |
-
"Rank": 32
|
| 1354 |
-
},
|
| 1355 |
-
"Social": {
|
| 1356 |
-
"Average Score": 0.179073276,
|
| 1357 |
-
"Standard Deviation": 0.02009658805,
|
| 1358 |
-
"Rank": 43
|
| 1359 |
-
}
|
| 1360 |
-
}
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"config": {
|
| 1364 |
-
"model_name": "llama3-8b-instruct",
|
| 1365 |
-
"organization": "Meta",
|
| 1366 |
-
"license": "Llama 3 Community",
|
| 1367 |
-
"knowledge_cutoff": "2024-01"
|
| 1368 |
-
},
|
| 1369 |
-
"results": {
|
| 1370 |
-
"OVERALL": {
|
| 1371 |
-
"Average Score": 0.367722676,
|
| 1372 |
-
"Standard Deviation": 0.1071368221,
|
| 1373 |
-
"Rank": 32
|
| 1374 |
-
},
|
| 1375 |
-
"Geometry": {
|
| 1376 |
-
"Average Score": 0.367143758,
|
| 1377 |
-
"Standard Deviation": 0.04363680358,
|
| 1378 |
-
"Rank": 35
|
| 1379 |
-
},
|
| 1380 |
-
"Algebra": {
|
| 1381 |
-
"Average Score": 0.391480973,
|
| 1382 |
-
"Standard Deviation": 0.02757445266,
|
| 1383 |
-
"Rank": 35
|
| 1384 |
-
},
|
| 1385 |
-
"Probability": {
|
| 1386 |
-
"Average Score": 0.317616445,
|
| 1387 |
-
"Standard Deviation": 0.04300430361,
|
| 1388 |
-
"Rank": 37
|
| 1389 |
-
},
|
| 1390 |
-
"Logical": {
|
| 1391 |
-
"Average Score": 0.461607495,
|
| 1392 |
-
"Standard Deviation": 0.02185028842,
|
| 1393 |
-
"Rank": 23
|
| 1394 |
-
},
|
| 1395 |
-
"Social": {
|
| 1396 |
-
"Average Score": 0.336373622,
|
| 1397 |
-
"Standard Deviation": 0.05762408512,
|
| 1398 |
-
"Rank": 28
|
| 1399 |
-
}
|
| 1400 |
-
}
|
| 1401 |
-
},
|
| 1402 |
-
{
|
| 1403 |
-
"config": {
|
| 1404 |
-
"model_name": "gemma-2-2b-it",
|
| 1405 |
-
"organization": "Google",
|
| 1406 |
-
"license": "Gemma License",
|
| 1407 |
-
"knowledge_cutoff": "2023-12"
|
| 1408 |
-
},
|
| 1409 |
-
"results": {
|
| 1410 |
-
"OVERALL": {
|
| 1411 |
-
"Average Score": 0.502167612,
|
| 1412 |
-
"Standard Deviation": 0.04389786763,
|
| 1413 |
-
"Rank": 20
|
| 1414 |
-
},
|
| 1415 |
-
"Geometry": {
|
| 1416 |
-
"Average Score": 0.395006676,
|
| 1417 |
-
"Standard Deviation": 0.05882607713,
|
| 1418 |
-
"Rank": 33
|
| 1419 |
-
},
|
| 1420 |
-
"Algebra": {
|
| 1421 |
-
"Average Score": 0.379391887,
|
| 1422 |
-
"Standard Deviation": 0.01722410785,
|
| 1423 |
-
"Rank": 36
|
| 1424 |
-
},
|
| 1425 |
-
"Probability": {
|
| 1426 |
-
"Average Score": 0.331231097,
|
| 1427 |
-
"Standard Deviation": 0.05392499987,
|
| 1428 |
-
"Rank": 36
|
| 1429 |
-
},
|
| 1430 |
-
"Logical": {
|
| 1431 |
-
"Average Score": 0.367687789,
|
| 1432 |
-
"Standard Deviation": 0.02547968808,
|
| 1433 |
-
"Rank": 27
|
| 1434 |
-
},
|
| 1435 |
-
"Social": {
|
| 1436 |
-
"Average Score": 0.393482094,
|
| 1437 |
-
"Standard Deviation": 0.06450214024,
|
| 1438 |
-
"Rank": 25
|
| 1439 |
-
}
|
| 1440 |
-
}
|
| 1441 |
-
},
|
| 1442 |
-
{
|
| 1443 |
-
"config": {
|
| 1444 |
-
"model_name": "starling-lm-7b-alpha",
|
| 1445 |
-
"organization": "Nexusflow",
|
| 1446 |
-
"license": "Apache-2.0",
|
| 1447 |
-
"knowledge_cutoff": "2023-12"
|
| 1448 |
-
},
|
| 1449 |
-
"results": {
|
| 1450 |
-
"OVERALL": {
|
| 1451 |
-
"Average Score": 0.366628765,
|
| 1452 |
-
"Standard Deviation": 0.08405492929,
|
| 1453 |
-
"Rank": 33
|
| 1454 |
-
},
|
| 1455 |
-
"Geometry": {
|
| 1456 |
-
"Average Score": 0.336782578,
|
| 1457 |
-
"Standard Deviation": 0.04069449132,
|
| 1458 |
-
"Rank": 36
|
| 1459 |
-
},
|
| 1460 |
-
"Algebra": {
|
| 1461 |
-
"Average Score": 0.371551932,
|
| 1462 |
-
"Standard Deviation": 0.03367241745,
|
| 1463 |
-
"Rank": 37
|
| 1464 |
-
},
|
| 1465 |
-
"Probability": {
|
| 1466 |
-
"Average Score": 0.331472505,
|
| 1467 |
-
"Standard Deviation": 0.04833324282,
|
| 1468 |
-
"Rank": 35
|
| 1469 |
-
},
|
| 1470 |
-
"Logical": {
|
| 1471 |
-
"Average Score": 0.260869624,
|
| 1472 |
-
"Standard Deviation": 0.03562735237,
|
| 1473 |
-
"Rank": 36
|
| 1474 |
-
},
|
| 1475 |
-
"Social": {
|
| 1476 |
-
"Average Score": 0.271975534,
|
| 1477 |
-
"Standard Deviation": 0.04266753408,
|
| 1478 |
-
"Rank": 35
|
| 1479 |
-
}
|
| 1480 |
-
}
|
| 1481 |
-
},
|
| 1482 |
-
{
|
| 1483 |
-
"config": {
|
| 1484 |
-
"model_name": "qwen1.5-4b-chat",
|
| 1485 |
-
"organization": "Alibaba",
|
| 1486 |
-
"license": "Qianwen LICENSE",
|
| 1487 |
-
"knowledge_cutoff": "2024-02"
|
| 1488 |
-
},
|
| 1489 |
-
"results": {
|
| 1490 |
-
"OVERALL": {
|
| 1491 |
-
"Average Score": 0.111876411,
|
| 1492 |
-
"Standard Deviation": 0.04241022785,
|
| 1493 |
-
"Rank": 49
|
| 1494 |
-
},
|
| 1495 |
-
"Geometry": {
|
| 1496 |
-
"Average Score": 0.215834522,
|
| 1497 |
-
"Standard Deviation": 0.0363766363,
|
| 1498 |
-
"Rank": 41
|
| 1499 |
-
},
|
| 1500 |
-
"Algebra": {
|
| 1501 |
-
"Average Score": 0.305589811,
|
| 1502 |
-
"Standard Deviation": 0.02354198912,
|
| 1503 |
-
"Rank": 38
|
| 1504 |
-
},
|
| 1505 |
-
"Probability": {
|
| 1506 |
-
"Average Score": 0.149365327,
|
| 1507 |
-
"Standard Deviation": 0.03489672675,
|
| 1508 |
-
"Rank": 45
|
| 1509 |
-
},
|
| 1510 |
-
"Logical": {
|
| 1511 |
-
"Average Score": 0.116210168,
|
| 1512 |
-
"Standard Deviation": 0.005927966496,
|
| 1513 |
-
"Rank": 47
|
| 1514 |
-
},
|
| 1515 |
-
"Social": {
|
| 1516 |
-
"Average Score": 0.18195615,
|
| 1517 |
-
"Standard Deviation": 0.02269805277,
|
| 1518 |
-
"Rank": 42
|
| 1519 |
-
}
|
| 1520 |
-
}
|
| 1521 |
-
},
|
| 1522 |
-
{
|
| 1523 |
-
"config": {
|
| 1524 |
-
"model_name": "command-r-(04-2024)",
|
| 1525 |
-
"organization": "Cohere",
|
| 1526 |
-
"license": "CC-BY-NC-4.0",
|
| 1527 |
-
"knowledge_cutoff": "2024-04"
|
| 1528 |
-
},
|
| 1529 |
-
"results": {
|
| 1530 |
-
"OVERALL": {
|
| 1531 |
-
"Average Score": 0.388783887,
|
| 1532 |
-
"Standard Deviation": 0.07417186783,
|
| 1533 |
-
"Rank": 30
|
| 1534 |
-
},
|
| 1535 |
-
"Geometry": {
|
| 1536 |
-
"Average Score": 0.300416698,
|
| 1537 |
-
"Standard Deviation": 0.03485612736,
|
| 1538 |
-
"Rank": 38
|
| 1539 |
-
},
|
| 1540 |
-
"Algebra": {
|
| 1541 |
-
"Average Score": 0.293120231,
|
| 1542 |
-
"Standard Deviation": 0.032926484,
|
| 1543 |
-
"Rank": 39
|
| 1544 |
-
},
|
| 1545 |
-
"Probability": {
|
| 1546 |
-
"Average Score": 0.281271304,
|
| 1547 |
-
"Standard Deviation": 0.05697149867,
|
| 1548 |
-
"Rank": 40
|
| 1549 |
-
},
|
| 1550 |
-
"Logical": {
|
| 1551 |
-
"Average Score": 0.276189906,
|
| 1552 |
-
"Standard Deviation": 0.03562914754,
|
| 1553 |
-
"Rank": 34
|
| 1554 |
-
},
|
| 1555 |
-
"Social": {
|
| 1556 |
-
"Average Score": 0.283882949,
|
| 1557 |
-
"Standard Deviation": 0.03336901148,
|
| 1558 |
-
"Rank": 33
|
| 1559 |
-
}
|
| 1560 |
-
}
|
| 1561 |
-
},
|
| 1562 |
-
{
|
| 1563 |
-
"config": {
|
| 1564 |
-
"model_name": "vicuna-33b",
|
| 1565 |
-
"organization": "LMSYS",
|
| 1566 |
-
"license": "Non-commercial",
|
| 1567 |
-
"knowledge_cutoff": "2023-12"
|
| 1568 |
-
},
|
| 1569 |
-
"results": {
|
| 1570 |
-
"OVERALL": {
|
| 1571 |
-
"Average Score": 0.316543555,
|
| 1572 |
-
"Standard Deviation": 0.08922095647,
|
| 1573 |
-
"Rank": 39
|
| 1574 |
-
},
|
| 1575 |
-
"Geometry": {
|
| 1576 |
-
"Average Score": 0.208284679,
|
| 1577 |
-
"Standard Deviation": 0.03937771461,
|
| 1578 |
-
"Rank": 42
|
| 1579 |
-
},
|
| 1580 |
-
"Algebra": {
|
| 1581 |
-
"Average Score": 0.248994048,
|
| 1582 |
-
"Standard Deviation": 0.02668175054,
|
| 1583 |
-
"Rank": 41
|
| 1584 |
-
},
|
| 1585 |
-
"Probability": {
|
| 1586 |
-
"Average Score": 0.222313995,
|
| 1587 |
-
"Standard Deviation": 0.03978859759,
|
| 1588 |
-
"Rank": 43
|
| 1589 |
-
},
|
| 1590 |
-
"Logical": {
|
| 1591 |
-
"Average Score": 0.180291222,
|
| 1592 |
-
"Standard Deviation": 0.021886267,
|
| 1593 |
-
"Rank": 42
|
| 1594 |
-
},
|
| 1595 |
-
"Social": {
|
| 1596 |
-
"Average Score": 0.257623798,
|
| 1597 |
-
"Standard Deviation": 0.02653724437,
|
| 1598 |
-
"Rank": 36
|
| 1599 |
-
}
|
| 1600 |
-
}
|
| 1601 |
-
},
|
| 1602 |
-
{
|
| 1603 |
-
"config": {
|
| 1604 |
-
"model_name": "gemma-7b-it",
|
| 1605 |
-
"organization": "Google",
|
| 1606 |
-
"license": "Gemma License",
|
| 1607 |
-
"knowledge_cutoff": "2023-12"
|
| 1608 |
-
},
|
| 1609 |
-
"results": {
|
| 1610 |
-
"OVERALL": {
|
| 1611 |
-
"Average Score": 0.285077558,
|
| 1612 |
-
"Standard Deviation": 0.08871758453,
|
| 1613 |
-
"Rank": 41
|
| 1614 |
-
},
|
| 1615 |
-
"Geometry": {
|
| 1616 |
-
"Average Score": 0.244791417,
|
| 1617 |
-
"Standard Deviation": 0.0289612078,
|
| 1618 |
-
"Rank": 39
|
| 1619 |
-
},
|
| 1620 |
-
"Algebra": {
|
| 1621 |
-
"Average Score": 0.250614794,
|
| 1622 |
-
"Standard Deviation": 0.01991678295,
|
| 1623 |
-
"Rank": 40
|
| 1624 |
-
},
|
| 1625 |
-
"Probability": {
|
| 1626 |
-
"Average Score": 0.174313053,
|
| 1627 |
-
"Standard Deviation": 0.03765424728,
|
| 1628 |
-
"Rank": 44
|
| 1629 |
-
},
|
| 1630 |
-
"Logical": {
|
| 1631 |
-
"Average Score": 0.197505536,
|
| 1632 |
-
"Standard Deviation": 0.02050298885,
|
| 1633 |
-
"Rank": 39
|
| 1634 |
-
},
|
| 1635 |
-
"Social": {
|
| 1636 |
-
"Average Score": 0.202138025,
|
| 1637 |
-
"Standard Deviation": 0.02098346639,
|
| 1638 |
-
"Rank": 41
|
| 1639 |
-
}
|
| 1640 |
-
}
|
| 1641 |
-
},
|
| 1642 |
-
{
|
| 1643 |
-
"config": {
|
| 1644 |
-
"model_name": "mistral-7b-instruct-2",
|
| 1645 |
-
"organization": "Mistral",
|
| 1646 |
-
"license": "Apache 2.0",
|
| 1647 |
-
"knowledge_cutoff": "2023-12"
|
| 1648 |
-
},
|
| 1649 |
-
"results": {
|
| 1650 |
-
"OVERALL": {
|
| 1651 |
-
"Average Score": 0.427513868,
|
| 1652 |
-
"Standard Deviation": 0.05553921135,
|
| 1653 |
-
"Rank": 27
|
| 1654 |
-
},
|
| 1655 |
-
"Geometry": {
|
| 1656 |
-
"Average Score": 0.216402626,
|
| 1657 |
-
"Standard Deviation": 0.03338414918,
|
| 1658 |
-
"Rank": 40
|
| 1659 |
-
},
|
| 1660 |
-
"Algebra": {
|
| 1661 |
-
"Average Score": 0.233777838,
|
| 1662 |
-
"Standard Deviation": 0.0155226054,
|
| 1663 |
-
"Rank": 42
|
| 1664 |
-
},
|
| 1665 |
-
"Probability": {
|
| 1666 |
-
"Average Score": 0.25118175,
|
| 1667 |
-
"Standard Deviation": 0.04065514593,
|
| 1668 |
-
"Rank": 41
|
| 1669 |
-
},
|
| 1670 |
-
"Logical": {
|
| 1671 |
-
"Average Score": 0.224469136,
|
| 1672 |
-
"Standard Deviation": 0.03404706752,
|
| 1673 |
-
"Rank": 37
|
| 1674 |
-
},
|
| 1675 |
-
"Social": {
|
| 1676 |
-
"Average Score": 0.209386782,
|
| 1677 |
-
"Standard Deviation": 0.02738569921,
|
| 1678 |
-
"Rank": 40
|
| 1679 |
-
}
|
| 1680 |
-
}
|
| 1681 |
-
},
|
| 1682 |
-
{
|
| 1683 |
-
"config": {
|
| 1684 |
-
"model_name": "mistral-7b-instruct-1",
|
| 1685 |
-
"organization": "Mistral",
|
| 1686 |
-
"license": "Apache 2.0",
|
| 1687 |
-
"knowledge_cutoff": "2023-12"
|
| 1688 |
-
},
|
| 1689 |
-
"results": {
|
| 1690 |
-
"OVERALL": {
|
| 1691 |
-
"Average Score": 0.23016314,
|
| 1692 |
-
"Standard Deviation": 0.07137625271,
|
| 1693 |
-
"Rank": 46
|
| 1694 |
-
},
|
| 1695 |
-
"Geometry": {
|
| 1696 |
-
"Average Score": 0.161799938,
|
| 1697 |
-
"Standard Deviation": 0.03595278559,
|
| 1698 |
-
"Rank": 46
|
| 1699 |
-
},
|
| 1700 |
-
"Algebra": {
|
| 1701 |
-
"Average Score": 0.210341624,
|
| 1702 |
-
"Standard Deviation": 0.01736539119,
|
| 1703 |
-
"Rank": 43
|
| 1704 |
-
},
|
| 1705 |
-
"Probability": {
|
| 1706 |
-
"Average Score": 0.238417922,
|
| 1707 |
-
"Standard Deviation": 0.03744211933,
|
| 1708 |
-
"Rank": 42
|
| 1709 |
-
},
|
| 1710 |
-
"Logical": {
|
| 1711 |
-
"Average Score": 0.142636601,
|
| 1712 |
-
"Standard Deviation": 0.02080406365,
|
| 1713 |
-
"Rank": 46
|
| 1714 |
-
},
|
| 1715 |
-
"Social": {
|
| 1716 |
-
"Average Score": 0.117646827,
|
| 1717 |
-
"Standard Deviation": 0.009321202779,
|
| 1718 |
-
"Rank": 49
|
| 1719 |
-
}
|
| 1720 |
-
}
|
| 1721 |
-
},
|
| 1722 |
-
{
|
| 1723 |
-
"config": {
|
| 1724 |
-
"model_name": "vicuna-13b",
|
| 1725 |
-
"organization": "LMSYS",
|
| 1726 |
-
"license": "Non-commercial",
|
| 1727 |
-
"knowledge_cutoff": "2023-11"
|
| 1728 |
-
},
|
| 1729 |
-
"results": {
|
| 1730 |
-
"OVERALL": {
|
| 1731 |
-
"Average Score": 0.201892849,
|
| 1732 |
-
"Standard Deviation": 0.06021749802,
|
| 1733 |
-
"Rank": 47
|
| 1734 |
-
},
|
| 1735 |
-
"Geometry": {
|
| 1736 |
-
"Average Score": 0.200941928,
|
| 1737 |
-
"Standard Deviation": 0.03366817781,
|
| 1738 |
-
"Rank": 43
|
| 1739 |
-
},
|
| 1740 |
-
"Algebra": {
|
| 1741 |
-
"Average Score": 0.196123323,
|
| 1742 |
-
"Standard Deviation": 0.0135715643,
|
| 1743 |
-
"Rank": 44
|
| 1744 |
-
},
|
| 1745 |
-
"Probability": {
|
| 1746 |
-
"Average Score": 0.141214079,
|
| 1747 |
-
"Standard Deviation": 0.02721328211,
|
| 1748 |
-
"Rank": 46
|
| 1749 |
-
},
|
| 1750 |
-
"Logical": {
|
| 1751 |
-
"Average Score": 0.148598631,
|
| 1752 |
-
"Standard Deviation": 0.02241523892,
|
| 1753 |
-
"Rank": 44
|
| 1754 |
-
},
|
| 1755 |
-
"Social": {
|
| 1756 |
-
"Average Score": 0.124655135,
|
| 1757 |
-
"Standard Deviation": 0.01122382671,
|
| 1758 |
-
"Rank": 48
|
| 1759 |
-
}
|
| 1760 |
-
}
|
| 1761 |
-
},
|
| 1762 |
-
{
|
| 1763 |
-
"config": {
|
| 1764 |
-
"model_name": "zephyr-7b-beta",
|
| 1765 |
-
"organization": "HuggingFace",
|
| 1766 |
-
"license": "MIT",
|
| 1767 |
-
"knowledge_cutoff": "2023-10"
|
| 1768 |
-
},
|
| 1769 |
-
"results": {
|
| 1770 |
-
"OVERALL": {
|
| 1771 |
-
"Average Score": 0.102705119,
|
| 1772 |
-
"Standard Deviation": 0.03683757312,
|
| 1773 |
-
"Rank": 50
|
| 1774 |
-
},
|
| 1775 |
-
"Geometry": {
|
| 1776 |
-
"Average Score": 0.114005544,
|
| 1777 |
-
"Standard Deviation": 0.03144354365,
|
| 1778 |
-
"Rank": 47
|
| 1779 |
-
},
|
| 1780 |
-
"Algebra": {
|
| 1781 |
-
"Average Score": 0.141766633,
|
| 1782 |
-
"Standard Deviation": 0.03179520129,
|
| 1783 |
-
"Rank": 45
|
| 1784 |
-
},
|
| 1785 |
-
"Probability": {
|
| 1786 |
-
"Average Score": 0.089050714,
|
| 1787 |
-
"Standard Deviation": 0.002136754266,
|
| 1788 |
-
"Rank": 49
|
| 1789 |
-
},
|
| 1790 |
-
"Logical": {
|
| 1791 |
-
"Average Score": 0.069520789,
|
| 1792 |
-
"Standard Deviation": 0.004477840857,
|
| 1793 |
-
"Rank": 51
|
| 1794 |
-
},
|
| 1795 |
-
"Social": {
|
| 1796 |
-
"Average Score": 0.0,
|
| 1797 |
-
"Standard Deviation": 0.0,
|
| 1798 |
-
"Rank": 54
|
| 1799 |
-
}
|
| 1800 |
-
}
|
| 1801 |
-
},
|
| 1802 |
-
{
|
| 1803 |
-
"config": {
|
| 1804 |
-
"model_name": "gemma-1.1-2b-it",
|
| 1805 |
-
"organization": "Google",
|
| 1806 |
-
"license": "Gemma License",
|
| 1807 |
-
"knowledge_cutoff": "2023-12"
|
| 1808 |
-
},
|
| 1809 |
-
"results": {
|
| 1810 |
-
"OVERALL": {
|
| 1811 |
-
"Average Score": 0.257700845,
|
| 1812 |
-
"Standard Deviation": 0.07369021445,
|
| 1813 |
-
"Rank": 44
|
| 1814 |
-
},
|
| 1815 |
-
"Geometry": {
|
| 1816 |
-
"Average Score": 0.183974034,
|
| 1817 |
-
"Standard Deviation": 0.0215548886,
|
| 1818 |
-
"Rank": 45
|
| 1819 |
-
},
|
| 1820 |
-
"Algebra": {
|
| 1821 |
-
"Average Score": 0.13422252,
|
| 1822 |
-
"Standard Deviation": 0.01922819511,
|
| 1823 |
-
"Rank": 46
|
| 1824 |
-
},
|
| 1825 |
-
"Probability": {
|
| 1826 |
-
"Average Score": 0.095628657,
|
| 1827 |
-
"Standard Deviation": 0.007536076456,
|
| 1828 |
-
"Rank": 48
|
| 1829 |
-
},
|
| 1830 |
-
"Logical": {
|
| 1831 |
-
"Average Score": 0.094965074,
|
| 1832 |
-
"Standard Deviation": 0.005019175487,
|
| 1833 |
-
"Rank": 49
|
| 1834 |
-
},
|
| 1835 |
-
"Social": {
|
| 1836 |
-
"Average Score": 0.167796727,
|
| 1837 |
-
"Standard Deviation": 0.01666541942,
|
| 1838 |
-
"Rank": 44
|
| 1839 |
-
}
|
| 1840 |
-
}
|
| 1841 |
-
},
|
| 1842 |
-
{
|
| 1843 |
-
"config": {
|
| 1844 |
-
"model_name": "llama2-7b-chat",
|
| 1845 |
-
"organization": "Meta",
|
| 1846 |
-
"license": "Llama 2 Community",
|
| 1847 |
-
"knowledge_cutoff": "2023-10"
|
| 1848 |
-
},
|
| 1849 |
-
"results": {
|
| 1850 |
-
"OVERALL": {
|
| 1851 |
-
"Average Score": 0.260189428,
|
| 1852 |
-
"Standard Deviation": 0.08019299364,
|
| 1853 |
-
"Rank": 43
|
| 1854 |
-
},
|
| 1855 |
-
"Geometry": {
|
| 1856 |
-
"Average Score": 0.087067276,
|
| 1857 |
-
"Standard Deviation": 0.04274343402,
|
| 1858 |
-
"Rank": 48
|
| 1859 |
-
},
|
| 1860 |
-
"Algebra": {
|
| 1861 |
-
"Average Score": 0.12308805,
|
| 1862 |
-
"Standard Deviation": 0.01856053622,
|
| 1863 |
-
"Rank": 47
|
| 1864 |
-
},
|
| 1865 |
-
"Probability": {
|
| 1866 |
-
"Average Score": 0.087515438,
|
| 1867 |
-
"Standard Deviation": 0.006315053573,
|
| 1868 |
-
"Rank": 50
|
| 1869 |
-
},
|
| 1870 |
-
"Logical": {
|
| 1871 |
-
"Average Score": 0.17312827,
|
| 1872 |
-
"Standard Deviation": 0.01867044092,
|
| 1873 |
-
"Rank": 43
|
| 1874 |
-
},
|
| 1875 |
-
"Social": {
|
| 1876 |
-
"Average Score": 0.152905272,
|
| 1877 |
-
"Standard Deviation": 0.007166957097,
|
| 1878 |
-
"Rank": 45
|
| 1879 |
-
}
|
| 1880 |
-
}
|
| 1881 |
-
},
|
| 1882 |
-
{
|
| 1883 |
-
"config": {
|
| 1884 |
-
"model_name": "gemma-2b-it",
|
| 1885 |
-
"organization": "Google",
|
| 1886 |
-
"license": "Gemma License",
|
| 1887 |
-
"knowledge_cutoff": "2023-11"
|
| 1888 |
-
},
|
| 1889 |
-
"results": {
|
| 1890 |
-
"OVERALL": {
|
| 1891 |
-
"Average Score": 0.234172069,
|
| 1892 |
-
"Standard Deviation": 0.06522685718,
|
| 1893 |
-
"Rank": 45
|
| 1894 |
-
},
|
| 1895 |
-
"Geometry": {
|
| 1896 |
-
"Average Score": 0.198571153,
|
| 1897 |
-
"Standard Deviation": 0.01699161031,
|
| 1898 |
-
"Rank": 44
|
| 1899 |
-
},
|
| 1900 |
-
"Algebra": {
|
| 1901 |
-
"Average Score": 0.109883009,
|
| 1902 |
-
"Standard Deviation": 0.01520005833,
|
| 1903 |
-
"Rank": 48
|
| 1904 |
-
},
|
| 1905 |
-
"Probability": {
|
| 1906 |
-
"Average Score": 0.06467432,
|
| 1907 |
-
"Standard Deviation": 0.002117497231,
|
| 1908 |
-
"Rank": 52
|
| 1909 |
-
},
|
| 1910 |
-
"Logical": {
|
| 1911 |
-
"Average Score": 0.039624492,
|
| 1912 |
-
"Standard Deviation": 0.007606972686,
|
| 1913 |
-
"Rank": 52
|
| 1914 |
-
},
|
| 1915 |
-
"Social": {
|
| 1916 |
-
"Average Score": 0.087452913,
|
| 1917 |
-
"Standard Deviation": 0.008170146562,
|
| 1918 |
-
"Rank": 52
|
| 1919 |
-
}
|
| 1920 |
-
}
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"config": {
|
| 1924 |
-
"model_name": "llama2-13b-chat",
|
| 1925 |
-
"organization": "Meta",
|
| 1926 |
-
"license": "Llama 2 Community",
|
| 1927 |
-
"knowledge_cutoff": "2023-12"
|
| 1928 |
-
},
|
| 1929 |
-
"results": {
|
| 1930 |
-
"OVERALL": {
|
| 1931 |
-
"Average Score": 0.263305684,
|
| 1932 |
-
"Standard Deviation": 0.07283640689,
|
| 1933 |
-
"Rank": 42
|
| 1934 |
-
},
|
| 1935 |
-
"Geometry": {
|
| 1936 |
-
"Average Score": 0.072729954,
|
| 1937 |
-
"Standard Deviation": 0.02315988261,
|
| 1938 |
-
"Rank": 50
|
| 1939 |
-
},
|
| 1940 |
-
"Algebra": {
|
| 1941 |
-
"Average Score": 0.080371692,
|
| 1942 |
-
"Standard Deviation": 0.01277569453,
|
| 1943 |
-
"Rank": 49
|
| 1944 |
-
},
|
| 1945 |
-
"Probability": {
|
| 1946 |
-
"Average Score": 0.117757344,
|
| 1947 |
-
"Standard Deviation": 0.02418619619,
|
| 1948 |
-
"Rank": 47
|
| 1949 |
-
},
|
| 1950 |
-
"Logical": {
|
| 1951 |
-
"Average Score": 0.193149889,
|
| 1952 |
-
"Standard Deviation": 0.01776690764,
|
| 1953 |
-
"Rank": 40
|
| 1954 |
-
},
|
| 1955 |
-
"Social": {
|
| 1956 |
-
"Average Score": 0.149125922,
|
| 1957 |
-
"Standard Deviation": 0.01157416827,
|
| 1958 |
-
"Rank": 46
|
| 1959 |
-
}
|
| 1960 |
-
}
|
| 1961 |
-
},
|
| 1962 |
-
{
|
| 1963 |
-
"config": {
|
| 1964 |
-
"model_name": "vicuna-7b",
|
| 1965 |
-
"organization": "LMSYS",
|
| 1966 |
-
"license": "Non-commercial",
|
| 1967 |
-
"knowledge_cutoff": "2023-11"
|
| 1968 |
-
},
|
| 1969 |
-
"results": {
|
| 1970 |
-
"OVERALL": {
|
| 1971 |
-
"Average Score": 0.198839786,
|
| 1972 |
-
"Standard Deviation": 0.05725381576,
|
| 1973 |
-
"Rank": 48
|
| 1974 |
-
},
|
| 1975 |
-
"Geometry": {
|
| 1976 |
-
"Average Score": 0.083457058,
|
| 1977 |
-
"Standard Deviation": 0.02520989111,
|
| 1978 |
-
"Rank": 49
|
| 1979 |
-
},
|
| 1980 |
-
"Algebra": {
|
| 1981 |
-
"Average Score": 0.070883882,
|
| 1982 |
-
"Standard Deviation": 0.007315853253,
|
| 1983 |
-
"Rank": 50
|
| 1984 |
-
},
|
| 1985 |
-
"Probability": {
|
| 1986 |
-
"Average Score": 0.080987673,
|
| 1987 |
-
"Standard Deviation": 0.005474288861,
|
| 1988 |
-
"Rank": 51
|
| 1989 |
-
},
|
| 1990 |
-
"Logical": {
|
| 1991 |
-
"Average Score": 0.100065588,
|
| 1992 |
-
"Standard Deviation": 0.003561886452,
|
| 1993 |
-
"Rank": 48
|
| 1994 |
-
},
|
| 1995 |
-
"Social": {
|
| 1996 |
-
"Average Score": 0.111076414,
|
| 1997 |
-
"Standard Deviation": 0.004805626512,
|
| 1998 |
-
"Rank": 50
|
| 1999 |
-
}
|
| 2000 |
-
}
|
| 2001 |
-
},
|
| 2002 |
-
{
|
| 2003 |
-
"config": {
|
| 2004 |
-
"model_name": "koala-13b",
|
| 2005 |
-
"organization": "UC Berkeley",
|
| 2006 |
-
"license": "Non-commercial",
|
| 2007 |
-
"knowledge_cutoff": "2023-10"
|
| 2008 |
-
},
|
| 2009 |
-
"results": {
|
| 2010 |
-
"OVERALL": {
|
| 2011 |
-
"Average Score": 0.09387188,
|
| 2012 |
-
"Standard Deviation": 0.02642167489,
|
| 2013 |
-
"Rank": 51
|
| 2014 |
-
},
|
| 2015 |
-
"Geometry": {
|
| 2016 |
-
"Average Score": 0.017374001,
|
| 2017 |
-
"Standard Deviation": 0.01747053557,
|
| 2018 |
-
"Rank": 51
|
| 2019 |
-
},
|
| 2020 |
-
"Algebra": {
|
| 2021 |
-
"Average Score": 0.018129197,
|
| 2022 |
-
"Standard Deviation": 0.01054371383,
|
| 2023 |
-
"Rank": 51
|
| 2024 |
-
},
|
| 2025 |
-
"Probability": {
|
| 2026 |
-
"Average Score": 0.043654362,
|
| 2027 |
-
"Standard Deviation": 0.004288231886,
|
| 2028 |
-
"Rank": 53
|
| 2029 |
-
},
|
| 2030 |
-
"Logical": {
|
| 2031 |
-
"Average Score": 0.074694053,
|
| 2032 |
-
"Standard Deviation": 0.002674646998,
|
| 2033 |
-
"Rank": 50
|
| 2034 |
-
},
|
| 2035 |
-
"Social": {
|
| 2036 |
-
"Average Score": 0.096983835,
|
| 2037 |
-
"Standard Deviation": 0.007847059783,
|
| 2038 |
-
"Rank": 51
|
| 2039 |
-
}
|
| 2040 |
-
}
|
| 2041 |
-
},
|
| 2042 |
-
{
|
| 2043 |
-
"config": {
|
| 2044 |
-
"model_name": "openassistant-pythia-12b",
|
| 2045 |
-
"organization": "OpenAssistant",
|
| 2046 |
-
"license": "Non-commercial",
|
| 2047 |
-
"knowledge_cutoff": "2023-09"
|
| 2048 |
-
},
|
| 2049 |
-
"results": {
|
| 2050 |
-
"OVERALL": {
|
| 2051 |
-
"Average Score": 0.0,
|
| 2052 |
-
"Standard Deviation": 0.0,
|
| 2053 |
-
"Rank": 52
|
| 2054 |
-
},
|
| 2055 |
-
"Geometry": {
|
| 2056 |
-
"Average Score": 0.0,
|
| 2057 |
-
"Standard Deviation": 0.0,
|
| 2058 |
-
"Rank": 52
|
| 2059 |
-
},
|
| 2060 |
-
"Algebra": {
|
| 2061 |
-
"Average Score": 0.0,
|
| 2062 |
-
"Standard Deviation": 0.0,
|
| 2063 |
-
"Rank": 52
|
| 2064 |
-
},
|
| 2065 |
-
"Probability": {
|
| 2066 |
-
"Average Score": 0.0,
|
| 2067 |
-
"Standard Deviation": 0.0,
|
| 2068 |
-
"Rank": 54
|
| 2069 |
-
},
|
| 2070 |
-
"Logical": {
|
| 2071 |
-
"Average Score": 0.0,
|
| 2072 |
-
"Standard Deviation": 0.0,
|
| 2073 |
-
"Rank": 53
|
| 2074 |
-
},
|
| 2075 |
-
"Social": {
|
| 2076 |
-
"Average Score": 0.030792528,
|
| 2077 |
-
"Standard Deviation": 0.007518796391,
|
| 2078 |
-
"Rank": 53
|
| 2079 |
-
}
|
| 2080 |
-
}
|
| 2081 |
-
}
|
| 2082 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/models_2024-10-08-17:39:21.001582.jsonl
DELETED
|
@@ -1,2082 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"config": {
|
| 4 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 5 |
-
"organization": "OpenAI",
|
| 6 |
-
"license": "Proprietary",
|
| 7 |
-
"knowledge_cutoff": "2023/10"
|
| 8 |
-
},
|
| 9 |
-
"results": {
|
| 10 |
-
"OVERALL": {
|
| 11 |
-
"Average Score": 0.974329609,
|
| 12 |
-
"Standard Deviation": 0.005024959031,
|
| 13 |
-
"Rank": 2
|
| 14 |
-
},
|
| 15 |
-
"Geometry": {
|
| 16 |
-
"Average Score": 0.976028578,
|
| 17 |
-
"Standard Deviation": 0.01507912373,
|
| 18 |
-
"Rank": 3
|
| 19 |
-
},
|
| 20 |
-
"Algebra": {
|
| 21 |
-
"Average Score": 0.951199453,
|
| 22 |
-
"Standard Deviation": 0.08452452108,
|
| 23 |
-
"Rank": 3
|
| 24 |
-
},
|
| 25 |
-
"Probability": {
|
| 26 |
-
"Average Score": 0.842116641,
|
| 27 |
-
"Standard Deviation": 0.006267759054,
|
| 28 |
-
"Rank": 3
|
| 29 |
-
},
|
| 30 |
-
"Logical": {
|
| 31 |
-
"Average Score": 0.828490728,
|
| 32 |
-
"Standard Deviation": 0.009134213144,
|
| 33 |
-
"Rank": 3
|
| 34 |
-
},
|
| 35 |
-
"Social": {
|
| 36 |
-
"Average Score": 0.815902987,
|
| 37 |
-
"Standard Deviation": 0.0196254222,
|
| 38 |
-
"Rank": 4
|
| 39 |
-
}
|
| 40 |
-
}
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"config": {
|
| 44 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 45 |
-
"organization": "OpenAI",
|
| 46 |
-
"license": "Proprietary",
|
| 47 |
-
"knowledge_cutoff": "2023/10"
|
| 48 |
-
},
|
| 49 |
-
"results": {
|
| 50 |
-
"OVERALL": {
|
| 51 |
-
"Average Score": 0.846571548,
|
| 52 |
-
"Standard Deviation": 0.03394056554,
|
| 53 |
-
"Rank": 6
|
| 54 |
-
},
|
| 55 |
-
"Geometry": {
|
| 56 |
-
"Average Score": 0.99773096,
|
| 57 |
-
"Standard Deviation": 0.002835555172,
|
| 58 |
-
"Rank": 1
|
| 59 |
-
},
|
| 60 |
-
"Algebra": {
|
| 61 |
-
"Average Score": 1.0,
|
| 62 |
-
"Standard Deviation": 0.0,
|
| 63 |
-
"Rank": 1
|
| 64 |
-
},
|
| 65 |
-
"Probability": {
|
| 66 |
-
"Average Score": 0.78855795,
|
| 67 |
-
"Standard Deviation": 0.008188675452,
|
| 68 |
-
"Rank": 6
|
| 69 |
-
},
|
| 70 |
-
"Logical": {
|
| 71 |
-
"Average Score": 0.668635768,
|
| 72 |
-
"Standard Deviation": 0.03466314094,
|
| 73 |
-
"Rank": 11
|
| 74 |
-
},
|
| 75 |
-
"Social": {
|
| 76 |
-
"Average Score": 0.680417314,
|
| 77 |
-
"Standard Deviation": 0.00656867063,
|
| 78 |
-
"Rank": 9
|
| 79 |
-
}
|
| 80 |
-
}
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"config": {
|
| 84 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 85 |
-
"organization": "OpenAI",
|
| 86 |
-
"license": "Proprietary",
|
| 87 |
-
"knowledge_cutoff": "2023/10"
|
| 88 |
-
},
|
| 89 |
-
"results": {
|
| 90 |
-
"OVERALL": {
|
| 91 |
-
"Average Score": 0.846334477,
|
| 92 |
-
"Standard Deviation": 0.09377911572,
|
| 93 |
-
"Rank": 7
|
| 94 |
-
},
|
| 95 |
-
"Geometry": {
|
| 96 |
-
"Average Score": 0.972472377,
|
| 97 |
-
"Standard Deviation": 0.01648274205,
|
| 98 |
-
"Rank": 4
|
| 99 |
-
},
|
| 100 |
-
"Algebra": {
|
| 101 |
-
"Average Score": 0.995511298,
|
| 102 |
-
"Standard Deviation": 0.004097802515,
|
| 103 |
-
"Rank": 2
|
| 104 |
-
},
|
| 105 |
-
"Probability": {
|
| 106 |
-
"Average Score": 0.812149974,
|
| 107 |
-
"Standard Deviation": 0.007669585485,
|
| 108 |
-
"Rank": 4
|
| 109 |
-
},
|
| 110 |
-
"Logical": {
|
| 111 |
-
"Average Score": 0.755019692,
|
| 112 |
-
"Standard Deviation": 0.008149588572,
|
| 113 |
-
"Rank": 6
|
| 114 |
-
},
|
| 115 |
-
"Social": {
|
| 116 |
-
"Average Score": 0.609875087,
|
| 117 |
-
"Standard Deviation": 0.038729239,
|
| 118 |
-
"Rank": 14
|
| 119 |
-
}
|
| 120 |
-
}
|
| 121 |
-
},
|
| 122 |
-
{
|
| 123 |
-
"config": {
|
| 124 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 125 |
-
"organization": "OpenAI",
|
| 126 |
-
"license": "Proprietary",
|
| 127 |
-
"knowledge_cutoff": "2023/12"
|
| 128 |
-
},
|
| 129 |
-
"results": {
|
| 130 |
-
"OVERALL": {
|
| 131 |
-
"Average Score": 0.855357972,
|
| 132 |
-
"Standard Deviation": 0.1016986368,
|
| 133 |
-
"Rank": 4
|
| 134 |
-
},
|
| 135 |
-
"Geometry": {
|
| 136 |
-
"Average Score": 0.95374588,
|
| 137 |
-
"Standard Deviation": 0.03109307166,
|
| 138 |
-
"Rank": 5
|
| 139 |
-
},
|
| 140 |
-
"Algebra": {
|
| 141 |
-
"Average Score": 0.930945223,
|
| 142 |
-
"Standard Deviation": 0.06705136813,
|
| 143 |
-
"Rank": 4
|
| 144 |
-
},
|
| 145 |
-
"Probability": {
|
| 146 |
-
"Average Score": 0.750705448,
|
| 147 |
-
"Standard Deviation": 0.05944483103,
|
| 148 |
-
"Rank": 8
|
| 149 |
-
},
|
| 150 |
-
"Logical": {
|
| 151 |
-
"Average Score": 0.77906699,
|
| 152 |
-
"Standard Deviation": 0.007406734161,
|
| 153 |
-
"Rank": 4
|
| 154 |
-
},
|
| 155 |
-
"Social": {
|
| 156 |
-
"Average Score": 0.715935163,
|
| 157 |
-
"Standard Deviation": 0.1209141409,
|
| 158 |
-
"Rank": 7
|
| 159 |
-
}
|
| 160 |
-
}
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"config": {
|
| 164 |
-
"model_name": "gemini-1.5-pro-001",
|
| 165 |
-
"organization": "Google",
|
| 166 |
-
"license": "Proprietary",
|
| 167 |
-
"knowledge_cutoff": "2023/11"
|
| 168 |
-
},
|
| 169 |
-
"results": {
|
| 170 |
-
"OVERALL": {
|
| 171 |
-
"Average Score": 0.797187842,
|
| 172 |
-
"Standard Deviation": 0.0272375249,
|
| 173 |
-
"Rank": 10
|
| 174 |
-
},
|
| 175 |
-
"Geometry": {
|
| 176 |
-
"Average Score": 0.9947169,
|
| 177 |
-
"Standard Deviation": 0.009150597621,
|
| 178 |
-
"Rank": 2
|
| 179 |
-
},
|
| 180 |
-
"Algebra": {
|
| 181 |
-
"Average Score": 0.857464301,
|
| 182 |
-
"Standard Deviation": 0.05014285338,
|
| 183 |
-
"Rank": 5
|
| 184 |
-
},
|
| 185 |
-
"Probability": {
|
| 186 |
-
"Average Score": 0.651781767,
|
| 187 |
-
"Standard Deviation": 0.04156998547,
|
| 188 |
-
"Rank": 12
|
| 189 |
-
},
|
| 190 |
-
"Logical": {
|
| 191 |
-
"Average Score": 0.739745471,
|
| 192 |
-
"Standard Deviation": 0.01631532019,
|
| 193 |
-
"Rank": 7
|
| 194 |
-
},
|
| 195 |
-
"Social": {
|
| 196 |
-
"Average Score": 0.649601885,
|
| 197 |
-
"Standard Deviation": 0.104854889,
|
| 198 |
-
"Rank": 12
|
| 199 |
-
}
|
| 200 |
-
}
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"config": {
|
| 204 |
-
"model_name": "qwen2-72b-instruct",
|
| 205 |
-
"organization": "Alibaba",
|
| 206 |
-
"license": "Qianwen LICENSE",
|
| 207 |
-
"knowledge_cutoff": "2024/09"
|
| 208 |
-
},
|
| 209 |
-
"results": {
|
| 210 |
-
"OVERALL": {
|
| 211 |
-
"Average Score": 0.737918558,
|
| 212 |
-
"Standard Deviation": 0.09069077339,
|
| 213 |
-
"Rank": 11
|
| 214 |
-
},
|
| 215 |
-
"Geometry": {
|
| 216 |
-
"Average Score": 0.796870305,
|
| 217 |
-
"Standard Deviation": 0.0509025346,
|
| 218 |
-
"Rank": 9
|
| 219 |
-
},
|
| 220 |
-
"Algebra": {
|
| 221 |
-
"Average Score": 0.836194231,
|
| 222 |
-
"Standard Deviation": 0.04517093028,
|
| 223 |
-
"Rank": 6
|
| 224 |
-
},
|
| 225 |
-
"Probability": {
|
| 226 |
-
"Average Score": 0.788068004,
|
| 227 |
-
"Standard Deviation": 0.007288989044,
|
| 228 |
-
"Rank": 7
|
| 229 |
-
},
|
| 230 |
-
"Logical": {
|
| 231 |
-
"Average Score": 0.619300904,
|
| 232 |
-
"Standard Deviation": 0.06377931612,
|
| 233 |
-
"Rank": 15
|
| 234 |
-
},
|
| 235 |
-
"Social": {
|
| 236 |
-
"Average Score": 0.652578786,
|
| 237 |
-
"Standard Deviation": 0.04259293171,
|
| 238 |
-
"Rank": 11
|
| 239 |
-
}
|
| 240 |
-
}
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"config": {
|
| 244 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 245 |
-
"organization": "OpenAI",
|
| 246 |
-
"license": "Proprietary",
|
| 247 |
-
"knowledge_cutoff": "2023/10"
|
| 248 |
-
},
|
| 249 |
-
"results": {
|
| 250 |
-
"OVERALL": {
|
| 251 |
-
"Average Score": 0.847694133,
|
| 252 |
-
"Standard Deviation": 0.02164304402,
|
| 253 |
-
"Rank": 5
|
| 254 |
-
},
|
| 255 |
-
"Geometry": {
|
| 256 |
-
"Average Score": 0.946650435,
|
| 257 |
-
"Standard Deviation": 0.01831236482,
|
| 258 |
-
"Rank": 7
|
| 259 |
-
},
|
| 260 |
-
"Algebra": {
|
| 261 |
-
"Average Score": 0.796243022,
|
| 262 |
-
"Standard Deviation": 0.05537539202,
|
| 263 |
-
"Rank": 7
|
| 264 |
-
},
|
| 265 |
-
"Probability": {
|
| 266 |
-
"Average Score": 0.798402685,
|
| 267 |
-
"Standard Deviation": 0.009404491967,
|
| 268 |
-
"Rank": 5
|
| 269 |
-
},
|
| 270 |
-
"Logical": {
|
| 271 |
-
"Average Score": 0.727009735,
|
| 272 |
-
"Standard Deviation": 0.02628110141,
|
| 273 |
-
"Rank": 8
|
| 274 |
-
},
|
| 275 |
-
"Social": {
|
| 276 |
-
"Average Score": 0.691949855,
|
| 277 |
-
"Standard Deviation": 0.02072934333,
|
| 278 |
-
"Rank": 8
|
| 279 |
-
}
|
| 280 |
-
}
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"config": {
|
| 284 |
-
"model_name": "claude-3.5-sonnet",
|
| 285 |
-
"organization": "Anthropic",
|
| 286 |
-
"license": "Proprietary",
|
| 287 |
-
"knowledge_cutoff": "2024/04"
|
| 288 |
-
},
|
| 289 |
-
"results": {
|
| 290 |
-
"OVERALL": {
|
| 291 |
-
"Average Score": 0.839004422,
|
| 292 |
-
"Standard Deviation": 0.1461079564,
|
| 293 |
-
"Rank": 8
|
| 294 |
-
},
|
| 295 |
-
"Geometry": {
|
| 296 |
-
"Average Score": 0.95316419,
|
| 297 |
-
"Standard Deviation": 0.02081192856,
|
| 298 |
-
"Rank": 6
|
| 299 |
-
},
|
| 300 |
-
"Algebra": {
|
| 301 |
-
"Average Score": 0.759789952,
|
| 302 |
-
"Standard Deviation": 0.02611765096,
|
| 303 |
-
"Rank": 8
|
| 304 |
-
},
|
| 305 |
-
"Probability": {
|
| 306 |
-
"Average Score": 0.707730127,
|
| 307 |
-
"Standard Deviation": 0.0394436664,
|
| 308 |
-
"Rank": 10
|
| 309 |
-
},
|
| 310 |
-
"Logical": {
|
| 311 |
-
"Average Score": 0.77342666,
|
| 312 |
-
"Standard Deviation": 0.002892426458,
|
| 313 |
-
"Rank": 5
|
| 314 |
-
},
|
| 315 |
-
"Social": {
|
| 316 |
-
"Average Score": 0.790002247,
|
| 317 |
-
"Standard Deviation": 0.1007410022,
|
| 318 |
-
"Rank": 5
|
| 319 |
-
}
|
| 320 |
-
}
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"config": {
|
| 324 |
-
"model_name": "o1-mini",
|
| 325 |
-
"organization": "OpenAI",
|
| 326 |
-
"license": "Proprietary",
|
| 327 |
-
"knowledge_cutoff": "2023/10"
|
| 328 |
-
},
|
| 329 |
-
"results": {
|
| 330 |
-
"OVERALL": {
|
| 331 |
-
"Average Score": 1.0,
|
| 332 |
-
"Standard Deviation": 0.0,
|
| 333 |
-
"Rank": 1
|
| 334 |
-
},
|
| 335 |
-
"Geometry": {
|
| 336 |
-
"Average Score": "N/A",
|
| 337 |
-
"Standard Deviation": "N/A",
|
| 338 |
-
"Rank": "N/A"
|
| 339 |
-
},
|
| 340 |
-
"Algebra": {
|
| 341 |
-
"Average Score": "N/A",
|
| 342 |
-
"Standard Deviation": "N/A",
|
| 343 |
-
"Rank": "N/A"
|
| 344 |
-
},
|
| 345 |
-
"Probability": {
|
| 346 |
-
"Average Score": 1.0,
|
| 347 |
-
"Standard Deviation": 0.0,
|
| 348 |
-
"Rank": 1
|
| 349 |
-
},
|
| 350 |
-
"Logical": {
|
| 351 |
-
"Average Score": 1.0,
|
| 352 |
-
"Standard Deviation": 0.0,
|
| 353 |
-
"Rank": 1
|
| 354 |
-
},
|
| 355 |
-
"Social": {
|
| 356 |
-
"Average Score": 0.993974241,
|
| 357 |
-
"Standard Deviation": 0.001996882328,
|
| 358 |
-
"Rank": 2
|
| 359 |
-
}
|
| 360 |
-
}
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"config": {
|
| 364 |
-
"model_name": "o1-preview",
|
| 365 |
-
"organization": "OpenAI",
|
| 366 |
-
"license": "Proprietary",
|
| 367 |
-
"knowledge_cutoff": "2023/10"
|
| 368 |
-
},
|
| 369 |
-
"results": {
|
| 370 |
-
"OVERALL": {
|
| 371 |
-
"Average Score": 0.945884589,
|
| 372 |
-
"Standard Deviation": 0.01059250762,
|
| 373 |
-
"Rank": 3
|
| 374 |
-
},
|
| 375 |
-
"Geometry": {
|
| 376 |
-
"Average Score": "N/A",
|
| 377 |
-
"Standard Deviation": "N/A",
|
| 378 |
-
"Rank": "N/A"
|
| 379 |
-
},
|
| 380 |
-
"Algebra": {
|
| 381 |
-
"Average Score": "N/A",
|
| 382 |
-
"Standard Deviation": "N/A",
|
| 383 |
-
"Rank": "N/A"
|
| 384 |
-
},
|
| 385 |
-
"Probability": {
|
| 386 |
-
"Average Score": 0.964666392,
|
| 387 |
-
"Standard Deviation": 0.003139983398,
|
| 388 |
-
"Rank": 2
|
| 389 |
-
},
|
| 390 |
-
"Logical": {
|
| 391 |
-
"Average Score": 0.987950057,
|
| 392 |
-
"Standard Deviation": 0.004881220327,
|
| 393 |
-
"Rank": 2
|
| 394 |
-
},
|
| 395 |
-
"Social": {
|
| 396 |
-
"Average Score": 1.0,
|
| 397 |
-
"Standard Deviation": 0.0,
|
| 398 |
-
"Rank": 1
|
| 399 |
-
}
|
| 400 |
-
}
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"config": {
|
| 404 |
-
"model_name": "gemini-1.5-flash-001",
|
| 405 |
-
"organization": "Google",
|
| 406 |
-
"license": "Proprietary",
|
| 407 |
-
"knowledge_cutoff": "2023/11"
|
| 408 |
-
},
|
| 409 |
-
"results": {
|
| 410 |
-
"OVERALL": {
|
| 411 |
-
"Average Score": 0.726493401,
|
| 412 |
-
"Standard Deviation": 0.01113913725,
|
| 413 |
-
"Rank": 12
|
| 414 |
-
},
|
| 415 |
-
"Geometry": {
|
| 416 |
-
"Average Score": 0.804144103,
|
| 417 |
-
"Standard Deviation": 0.1327142178,
|
| 418 |
-
"Rank": 8
|
| 419 |
-
},
|
| 420 |
-
"Algebra": {
|
| 421 |
-
"Average Score": 0.731776765,
|
| 422 |
-
"Standard Deviation": 0.02594657111,
|
| 423 |
-
"Rank": 11
|
| 424 |
-
},
|
| 425 |
-
"Probability": {
|
| 426 |
-
"Average Score": 0.614461891,
|
| 427 |
-
"Standard Deviation": 0.04690131826,
|
| 428 |
-
"Rank": 15
|
| 429 |
-
},
|
| 430 |
-
"Logical": {
|
| 431 |
-
"Average Score": 0.630805991,
|
| 432 |
-
"Standard Deviation": 0.04871350612,
|
| 433 |
-
"Rank": 13
|
| 434 |
-
},
|
| 435 |
-
"Social": {
|
| 436 |
-
"Average Score": 0.555933822,
|
| 437 |
-
"Standard Deviation": 0.1029934524,
|
| 438 |
-
"Rank": 16
|
| 439 |
-
}
|
| 440 |
-
}
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"config": {
|
| 444 |
-
"model_name": "gpt4-1106",
|
| 445 |
-
"organization": "OpenAI",
|
| 446 |
-
"license": "Proprietary",
|
| 447 |
-
"knowledge_cutoff": "2024/04"
|
| 448 |
-
},
|
| 449 |
-
"results": {
|
| 450 |
-
"OVERALL": {
|
| 451 |
-
"Average Score": 0.816347784,
|
| 452 |
-
"Standard Deviation": 0.1566815755,
|
| 453 |
-
"Rank": 9
|
| 454 |
-
},
|
| 455 |
-
"Geometry": {
|
| 456 |
-
"Average Score": 0.71843088,
|
| 457 |
-
"Standard Deviation": 0.04778038294,
|
| 458 |
-
"Rank": 13
|
| 459 |
-
},
|
| 460 |
-
"Algebra": {
|
| 461 |
-
"Average Score": 0.712910417,
|
| 462 |
-
"Standard Deviation": 0.02581828898,
|
| 463 |
-
"Rank": 12
|
| 464 |
-
},
|
| 465 |
-
"Probability": {
|
| 466 |
-
"Average Score": 0.623947619,
|
| 467 |
-
"Standard Deviation": 0.03502982933,
|
| 468 |
-
"Rank": 14
|
| 469 |
-
},
|
| 470 |
-
"Logical": {
|
| 471 |
-
"Average Score": 0.637482274,
|
| 472 |
-
"Standard Deviation": 0.04158809888,
|
| 473 |
-
"Rank": 12
|
| 474 |
-
},
|
| 475 |
-
"Social": {
|
| 476 |
-
"Average Score": 0.450609816,
|
| 477 |
-
"Standard Deviation": 0.05208655446,
|
| 478 |
-
"Rank": 23
|
| 479 |
-
}
|
| 480 |
-
}
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"config": {
|
| 484 |
-
"model_name": "gemma-2-27b-it",
|
| 485 |
-
"organization": "Google",
|
| 486 |
-
"license": "Gemma License",
|
| 487 |
-
"knowledge_cutoff": "2024/06"
|
| 488 |
-
},
|
| 489 |
-
"results": {
|
| 490 |
-
"OVERALL": {
|
| 491 |
-
"Average Score": 0.624169623,
|
| 492 |
-
"Standard Deviation": 0.1048365121,
|
| 493 |
-
"Rank": 15
|
| 494 |
-
},
|
| 495 |
-
"Geometry": {
|
| 496 |
-
"Average Score": 0.60112744,
|
| 497 |
-
"Standard Deviation": 0.0469109952,
|
| 498 |
-
"Rank": 19
|
| 499 |
-
},
|
| 500 |
-
"Algebra": {
|
| 501 |
-
"Average Score": 0.687955914,
|
| 502 |
-
"Standard Deviation": 0.01959958192,
|
| 503 |
-
"Rank": 13
|
| 504 |
-
},
|
| 505 |
-
"Probability": {
|
| 506 |
-
"Average Score": 0.589524771,
|
| 507 |
-
"Standard Deviation": 0.03112689325,
|
| 508 |
-
"Rank": 16
|
| 509 |
-
},
|
| 510 |
-
"Logical": {
|
| 511 |
-
"Average Score": 0.614978944,
|
| 512 |
-
"Standard Deviation": 0.05710657859,
|
| 513 |
-
"Rank": 16
|
| 514 |
-
},
|
| 515 |
-
"Social": {
|
| 516 |
-
"Average Score": 0.487844257,
|
| 517 |
-
"Standard Deviation": 0.05857760809,
|
| 518 |
-
"Rank": 20
|
| 519 |
-
}
|
| 520 |
-
}
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"config": {
|
| 524 |
-
"model_name": "claude-3-opus",
|
| 525 |
-
"organization": "Anthropic",
|
| 526 |
-
"license": "Proprietary",
|
| 527 |
-
"knowledge_cutoff": "2023/08"
|
| 528 |
-
},
|
| 529 |
-
"results": {
|
| 530 |
-
"OVERALL": {
|
| 531 |
-
"Average Score": 0.650636271,
|
| 532 |
-
"Standard Deviation": 0.1197773541,
|
| 533 |
-
"Rank": 14
|
| 534 |
-
},
|
| 535 |
-
"Geometry": {
|
| 536 |
-
"Average Score": 0.7215743,
|
| 537 |
-
"Standard Deviation": 0.04712598358,
|
| 538 |
-
"Rank": 12
|
| 539 |
-
},
|
| 540 |
-
"Algebra": {
|
| 541 |
-
"Average Score": 0.68777327,
|
| 542 |
-
"Standard Deviation": 0.02382683713,
|
| 543 |
-
"Rank": 14
|
| 544 |
-
},
|
| 545 |
-
"Probability": {
|
| 546 |
-
"Average Score": 0.626471421,
|
| 547 |
-
"Standard Deviation": 0.02911817976,
|
| 548 |
-
"Rank": 13
|
| 549 |
-
},
|
| 550 |
-
"Logical": {
|
| 551 |
-
"Average Score": 0.692346381,
|
| 552 |
-
"Standard Deviation": 0.03617185198,
|
| 553 |
-
"Rank": 10
|
| 554 |
-
},
|
| 555 |
-
"Social": {
|
| 556 |
-
"Average Score": 0.663410854,
|
| 557 |
-
"Standard Deviation": 0.09540220876,
|
| 558 |
-
"Rank": 10
|
| 559 |
-
}
|
| 560 |
-
}
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"config": {
|
| 564 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 565 |
-
"organization": "Google",
|
| 566 |
-
"license": "Gemma License",
|
| 567 |
-
"knowledge_cutoff": "2024/07"
|
| 568 |
-
},
|
| 569 |
-
"results": {
|
| 570 |
-
"OVERALL": {
|
| 571 |
-
"Average Score": "N/A",
|
| 572 |
-
"Standard Deviation": "N/A",
|
| 573 |
-
"Rank": "N/A"
|
| 574 |
-
},
|
| 575 |
-
"Geometry": {
|
| 576 |
-
"Average Score": 0.582787508,
|
| 577 |
-
"Standard Deviation": 0.03965204074,
|
| 578 |
-
"Rank": 20
|
| 579 |
-
},
|
| 580 |
-
"Algebra": {
|
| 581 |
-
"Average Score": 0.658648133,
|
| 582 |
-
"Standard Deviation": 0.02565919856,
|
| 583 |
-
"Rank": 15
|
| 584 |
-
},
|
| 585 |
-
"Probability": {
|
| 586 |
-
"Average Score": 0.547861265,
|
| 587 |
-
"Standard Deviation": 0.02885209131,
|
| 588 |
-
"Rank": 19
|
| 589 |
-
},
|
| 590 |
-
"Logical": {
|
| 591 |
-
"Average Score": 0.540720893,
|
| 592 |
-
"Standard Deviation": 0.01970134508,
|
| 593 |
-
"Rank": 20
|
| 594 |
-
},
|
| 595 |
-
"Social": {
|
| 596 |
-
"Average Score": 0.635266187,
|
| 597 |
-
"Standard Deviation": 0.03620021751,
|
| 598 |
-
"Rank": 13
|
| 599 |
-
}
|
| 600 |
-
}
|
| 601 |
-
},
|
| 602 |
-
{
|
| 603 |
-
"config": {
|
| 604 |
-
"model_name": "qwen1.5-72b-chat",
|
| 605 |
-
"organization": "Alibaba",
|
| 606 |
-
"license": "Qianwen LICENSE",
|
| 607 |
-
"knowledge_cutoff": "2024/03"
|
| 608 |
-
},
|
| 609 |
-
"results": {
|
| 610 |
-
"OVERALL": {
|
| 611 |
-
"Average Score": 0.519549796,
|
| 612 |
-
"Standard Deviation": 0.00903634343,
|
| 613 |
-
"Rank": 18
|
| 614 |
-
},
|
| 615 |
-
"Geometry": {
|
| 616 |
-
"Average Score": 0.543139301,
|
| 617 |
-
"Standard Deviation": 0.03425202326,
|
| 618 |
-
"Rank": 24
|
| 619 |
-
},
|
| 620 |
-
"Algebra": {
|
| 621 |
-
"Average Score": 0.635228729,
|
| 622 |
-
"Standard Deviation": 0.01944043425,
|
| 623 |
-
"Rank": 16
|
| 624 |
-
},
|
| 625 |
-
"Probability": {
|
| 626 |
-
"Average Score": 0.486948658,
|
| 627 |
-
"Standard Deviation": 0.06064655315,
|
| 628 |
-
"Rank": 23
|
| 629 |
-
},
|
| 630 |
-
"Logical": {
|
| 631 |
-
"Average Score": 0.284069394,
|
| 632 |
-
"Standard Deviation": 0.02686608506,
|
| 633 |
-
"Rank": 33
|
| 634 |
-
},
|
| 635 |
-
"Social": {
|
| 636 |
-
"Average Score": 0.415007627,
|
| 637 |
-
"Standard Deviation": 0.03920053159,
|
| 638 |
-
"Rank": 24
|
| 639 |
-
}
|
| 640 |
-
}
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"config": {
|
| 644 |
-
"model_name": "qwen1.5-32b-chat",
|
| 645 |
-
"organization": "Alibaba",
|
| 646 |
-
"license": "Qianwen LICENSE",
|
| 647 |
-
"knowledge_cutoff": "2024/03"
|
| 648 |
-
},
|
| 649 |
-
"results": {
|
| 650 |
-
"OVERALL": {
|
| 651 |
-
"Average Score": 0.393789407,
|
| 652 |
-
"Standard Deviation": 0.05413770095,
|
| 653 |
-
"Rank": 29
|
| 654 |
-
},
|
| 655 |
-
"Geometry": {
|
| 656 |
-
"Average Score": 0.51086835,
|
| 657 |
-
"Standard Deviation": 0.04052471998,
|
| 658 |
-
"Rank": 27
|
| 659 |
-
},
|
| 660 |
-
"Algebra": {
|
| 661 |
-
"Average Score": 0.609003168,
|
| 662 |
-
"Standard Deviation": 0.04874143541,
|
| 663 |
-
"Rank": 17
|
| 664 |
-
},
|
| 665 |
-
"Probability": {
|
| 666 |
-
"Average Score": 0.476300002,
|
| 667 |
-
"Standard Deviation": 0.05322403912,
|
| 668 |
-
"Rank": 24
|
| 669 |
-
},
|
| 670 |
-
"Logical": {
|
| 671 |
-
"Average Score": 0.331781014,
|
| 672 |
-
"Standard Deviation": 0.004938997686,
|
| 673 |
-
"Rank": 30
|
| 674 |
-
},
|
| 675 |
-
"Social": {
|
| 676 |
-
"Average Score": 0.380987334,
|
| 677 |
-
"Standard Deviation": 0.03762251776,
|
| 678 |
-
"Rank": 26
|
| 679 |
-
}
|
| 680 |
-
}
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"config": {
|
| 684 |
-
"model_name": "google-gemma-2-9b-it",
|
| 685 |
-
"organization": "Google",
|
| 686 |
-
"license": "Proprietary",
|
| 687 |
-
"knowledge_cutoff": "2024/06"
|
| 688 |
-
},
|
| 689 |
-
"results": {
|
| 690 |
-
"OVERALL": {
|
| 691 |
-
"Average Score": 0.489663449,
|
| 692 |
-
"Standard Deviation": 0.002595702019,
|
| 693 |
-
"Rank": 21
|
| 694 |
-
},
|
| 695 |
-
"Geometry": {
|
| 696 |
-
"Average Score": 0.575371308,
|
| 697 |
-
"Standard Deviation": 0.03556220251,
|
| 698 |
-
"Rank": 22
|
| 699 |
-
},
|
| 700 |
-
"Algebra": {
|
| 701 |
-
"Average Score": 0.597045661,
|
| 702 |
-
"Standard Deviation": 0.0313828123,
|
| 703 |
-
"Rank": 18
|
| 704 |
-
},
|
| 705 |
-
"Probability": {
|
| 706 |
-
"Average Score": 0.589221807,
|
| 707 |
-
"Standard Deviation": 0.03110811656,
|
| 708 |
-
"Rank": 18
|
| 709 |
-
},
|
| 710 |
-
"Logical": {
|
| 711 |
-
"Average Score": 0.587579897,
|
| 712 |
-
"Standard Deviation": 0.05512716783,
|
| 713 |
-
"Rank": 18
|
| 714 |
-
},
|
| 715 |
-
"Social": {
|
| 716 |
-
"Average Score": 0.768337958,
|
| 717 |
-
"Standard Deviation": 0.04078610476,
|
| 718 |
-
"Rank": 6
|
| 719 |
-
}
|
| 720 |
-
}
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"config": {
|
| 724 |
-
"model_name": "yi-1.5-34b-chat",
|
| 725 |
-
"organization": "01 AI",
|
| 726 |
-
"license": "Proprietary",
|
| 727 |
-
"knowledge_cutoff": "2024/05"
|
| 728 |
-
},
|
| 729 |
-
"results": {
|
| 730 |
-
"OVERALL": {
|
| 731 |
-
"Average Score": 0.607812897,
|
| 732 |
-
"Standard Deviation": 0.1440881293,
|
| 733 |
-
"Rank": 16
|
| 734 |
-
},
|
| 735 |
-
"Geometry": {
|
| 736 |
-
"Average Score": 0.566666724,
|
| 737 |
-
"Standard Deviation": 0.04001381658,
|
| 738 |
-
"Rank": 23
|
| 739 |
-
},
|
| 740 |
-
"Algebra": {
|
| 741 |
-
"Average Score": 0.590997292,
|
| 742 |
-
"Standard Deviation": 0.03594087315,
|
| 743 |
-
"Rank": 19
|
| 744 |
-
},
|
| 745 |
-
"Probability": {
|
| 746 |
-
"Average Score": 0.589524589,
|
| 747 |
-
"Standard Deviation": 0.03112618772,
|
| 748 |
-
"Rank": 17
|
| 749 |
-
},
|
| 750 |
-
"Logical": {
|
| 751 |
-
"Average Score": 0.574105508,
|
| 752 |
-
"Standard Deviation": 0.03441737941,
|
| 753 |
-
"Rank": 19
|
| 754 |
-
},
|
| 755 |
-
"Social": {
|
| 756 |
-
"Average Score": 0.516980832,
|
| 757 |
-
"Standard Deviation": 0.03369347985,
|
| 758 |
-
"Rank": 19
|
| 759 |
-
}
|
| 760 |
-
}
|
| 761 |
-
},
|
| 762 |
-
{
|
| 763 |
-
"config": {
|
| 764 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 765 |
-
"organization": "Meta",
|
| 766 |
-
"license": "Llama 3.1 Community",
|
| 767 |
-
"knowledge_cutoff": "2023/12"
|
| 768 |
-
},
|
| 769 |
-
"results": {
|
| 770 |
-
"OVERALL": {
|
| 771 |
-
"Average Score": 0.505936324,
|
| 772 |
-
"Standard Deviation": 0.05286756493,
|
| 773 |
-
"Rank": 19
|
| 774 |
-
},
|
| 775 |
-
"Geometry": {
|
| 776 |
-
"Average Score": 0.522442162,
|
| 777 |
-
"Standard Deviation": 0.03908236317,
|
| 778 |
-
"Rank": 25
|
| 779 |
-
},
|
| 780 |
-
"Algebra": {
|
| 781 |
-
"Average Score": 0.582702645,
|
| 782 |
-
"Standard Deviation": 0.05002277711,
|
| 783 |
-
"Rank": 20
|
| 784 |
-
},
|
| 785 |
-
"Probability": {
|
| 786 |
-
"Average Score": 0.495001149,
|
| 787 |
-
"Standard Deviation": 0.05244587037,
|
| 788 |
-
"Rank": 22
|
| 789 |
-
},
|
| 790 |
-
"Logical": {
|
| 791 |
-
"Average Score": 0.443030561,
|
| 792 |
-
"Standard Deviation": 0.01343820628,
|
| 793 |
-
"Rank": 25
|
| 794 |
-
},
|
| 795 |
-
"Social": {
|
| 796 |
-
"Average Score": 0.329195941,
|
| 797 |
-
"Standard Deviation": 0.03925019528,
|
| 798 |
-
"Rank": 30
|
| 799 |
-
}
|
| 800 |
-
}
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"config": {
|
| 804 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 805 |
-
"organization": "OpenAI",
|
| 806 |
-
"license": "Proprietary",
|
| 807 |
-
"knowledge_cutoff": "2021/09"
|
| 808 |
-
},
|
| 809 |
-
"results": {
|
| 810 |
-
"OVERALL": {
|
| 811 |
-
"Average Score": 0.313398088,
|
| 812 |
-
"Standard Deviation": 0.09322528606,
|
| 813 |
-
"Rank": 40
|
| 814 |
-
},
|
| 815 |
-
"Geometry": {
|
| 816 |
-
"Average Score": 0.678714519,
|
| 817 |
-
"Standard Deviation": 0.05926546762,
|
| 818 |
-
"Rank": 14
|
| 819 |
-
},
|
| 820 |
-
"Algebra": {
|
| 821 |
-
"Average Score": 0.569296173,
|
| 822 |
-
"Standard Deviation": 0.05277281097,
|
| 823 |
-
"Rank": 21
|
| 824 |
-
},
|
| 825 |
-
"Probability": {
|
| 826 |
-
"Average Score": 0.448460767,
|
| 827 |
-
"Standard Deviation": 0.05768095196,
|
| 828 |
-
"Rank": 26
|
| 829 |
-
},
|
| 830 |
-
"Logical": {
|
| 831 |
-
"Average Score": 0.148521348,
|
| 832 |
-
"Standard Deviation": 0.04033712907,
|
| 833 |
-
"Rank": 45
|
| 834 |
-
},
|
| 835 |
-
"Social": {
|
| 836 |
-
"Average Score": 0.235071541,
|
| 837 |
-
"Standard Deviation": 0.02632892457,
|
| 838 |
-
"Rank": 39
|
| 839 |
-
}
|
| 840 |
-
}
|
| 841 |
-
},
|
| 842 |
-
{
|
| 843 |
-
"config": {
|
| 844 |
-
"model_name": "llama-3-70b-instruct",
|
| 845 |
-
"organization": "Meta",
|
| 846 |
-
"license": "Llama 3 Community",
|
| 847 |
-
"knowledge_cutoff": "2023/12"
|
| 848 |
-
},
|
| 849 |
-
"results": {
|
| 850 |
-
"OVERALL": {
|
| 851 |
-
"Average Score": 0.456689885,
|
| 852 |
-
"Standard Deviation": 0.01385989995,
|
| 853 |
-
"Rank": 23
|
| 854 |
-
},
|
| 855 |
-
"Geometry": {
|
| 856 |
-
"Average Score": 0.516865529,
|
| 857 |
-
"Standard Deviation": 0.03858112564,
|
| 858 |
-
"Rank": 26
|
| 859 |
-
},
|
| 860 |
-
"Algebra": {
|
| 861 |
-
"Average Score": 0.566756531,
|
| 862 |
-
"Standard Deviation": 0.03369826926,
|
| 863 |
-
"Rank": 22
|
| 864 |
-
},
|
| 865 |
-
"Probability": {
|
| 866 |
-
"Average Score": 0.513857306,
|
| 867 |
-
"Standard Deviation": 0.05453699062,
|
| 868 |
-
"Rank": 21
|
| 869 |
-
},
|
| 870 |
-
"Logical": {
|
| 871 |
-
"Average Score": 0.713796415,
|
| 872 |
-
"Standard Deviation": 0.02031215107,
|
| 873 |
-
"Rank": 9
|
| 874 |
-
},
|
| 875 |
-
"Social": {
|
| 876 |
-
"Average Score": 0.45872939,
|
| 877 |
-
"Standard Deviation": 0.05347039576,
|
| 878 |
-
"Rank": 22
|
| 879 |
-
}
|
| 880 |
-
}
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"config": {
|
| 884 |
-
"model_name": "claude-3-sonnet",
|
| 885 |
-
"organization": "Anthropic",
|
| 886 |
-
"license": "Proprietary",
|
| 887 |
-
"knowledge_cutoff": "2023/08"
|
| 888 |
-
},
|
| 889 |
-
"results": {
|
| 890 |
-
"OVERALL": {
|
| 891 |
-
"Average Score": 0.520010833,
|
| 892 |
-
"Standard Deviation": 0.005030563799,
|
| 893 |
-
"Rank": 17
|
| 894 |
-
},
|
| 895 |
-
"Geometry": {
|
| 896 |
-
"Average Score": 0.675613638,
|
| 897 |
-
"Standard Deviation": 0.05275594408,
|
| 898 |
-
"Rank": 15
|
| 899 |
-
},
|
| 900 |
-
"Algebra": {
|
| 901 |
-
"Average Score": 0.552025728,
|
| 902 |
-
"Standard Deviation": 0.04122192409,
|
| 903 |
-
"Rank": 23
|
| 904 |
-
},
|
| 905 |
-
"Probability": {
|
| 906 |
-
"Average Score": 0.516192848,
|
| 907 |
-
"Standard Deviation": 0.04152293217,
|
| 908 |
-
"Rank": 20
|
| 909 |
-
},
|
| 910 |
-
"Logical": {
|
| 911 |
-
"Average Score": 0.588545747,
|
| 912 |
-
"Standard Deviation": 0.06068211943,
|
| 913 |
-
"Rank": 17
|
| 914 |
-
},
|
| 915 |
-
"Social": {
|
| 916 |
-
"Average Score": 0.570437582,
|
| 917 |
-
"Standard Deviation": 0.08607040862,
|
| 918 |
-
"Rank": 15
|
| 919 |
-
}
|
| 920 |
-
}
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"config": {
|
| 924 |
-
"model_name": "qwen1.5-14b-chat",
|
| 925 |
-
"organization": "Alibaba",
|
| 926 |
-
"license": "Qianwen LICENSE",
|
| 927 |
-
"knowledge_cutoff": "2024/02"
|
| 928 |
-
},
|
| 929 |
-
"results": {
|
| 930 |
-
"OVERALL": {
|
| 931 |
-
"Average Score": 0.415328996,
|
| 932 |
-
"Standard Deviation": 0.0743938717,
|
| 933 |
-
"Rank": 28
|
| 934 |
-
},
|
| 935 |
-
"Geometry": {
|
| 936 |
-
"Average Score": 0.452504016,
|
| 937 |
-
"Standard Deviation": 0.04225594393,
|
| 938 |
-
"Rank": 28
|
| 939 |
-
},
|
| 940 |
-
"Algebra": {
|
| 941 |
-
"Average Score": 0.538655725,
|
| 942 |
-
"Standard Deviation": 0.03721542594,
|
| 943 |
-
"Rank": 24
|
| 944 |
-
},
|
| 945 |
-
"Probability": {
|
| 946 |
-
"Average Score": 0.397185975,
|
| 947 |
-
"Standard Deviation": 0.05607695946,
|
| 948 |
-
"Rank": 30
|
| 949 |
-
},
|
| 950 |
-
"Logical": {
|
| 951 |
-
"Average Score": 0.264573129,
|
| 952 |
-
"Standard Deviation": 0.03936133174,
|
| 953 |
-
"Rank": 35
|
| 954 |
-
},
|
| 955 |
-
"Social": {
|
| 956 |
-
"Average Score": 0.287370142,
|
| 957 |
-
"Standard Deviation": 0.04264085315,
|
| 958 |
-
"Rank": 32
|
| 959 |
-
}
|
| 960 |
-
}
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"config": {
|
| 964 |
-
"model_name": "claude-3-haiku",
|
| 965 |
-
"organization": "Anthropic",
|
| 966 |
-
"license": "Proprietary",
|
| 967 |
-
"knowledge_cutoff": "2023/08"
|
| 968 |
-
},
|
| 969 |
-
"results": {
|
| 970 |
-
"OVERALL": {
|
| 971 |
-
"Average Score": 0.453901163,
|
| 972 |
-
"Standard Deviation": 0.003604084261,
|
| 973 |
-
"Rank": 24
|
| 974 |
-
},
|
| 975 |
-
"Geometry": {
|
| 976 |
-
"Average Score": 0.607993912,
|
| 977 |
-
"Standard Deviation": 0.05793460748,
|
| 978 |
-
"Rank": 17
|
| 979 |
-
},
|
| 980 |
-
"Algebra": {
|
| 981 |
-
"Average Score": 0.520054055,
|
| 982 |
-
"Standard Deviation": 0.03333544511,
|
| 983 |
-
"Rank": 25
|
| 984 |
-
},
|
| 985 |
-
"Probability": {
|
| 986 |
-
"Average Score": 0.474460688,
|
| 987 |
-
"Standard Deviation": 0.0446501933,
|
| 988 |
-
"Rank": 25
|
| 989 |
-
},
|
| 990 |
-
"Logical": {
|
| 991 |
-
"Average Score": 0.512815976,
|
| 992 |
-
"Standard Deviation": 0.0163264281,
|
| 993 |
-
"Rank": 21
|
| 994 |
-
},
|
| 995 |
-
"Social": {
|
| 996 |
-
"Average Score": 0.551083976,
|
| 997 |
-
"Standard Deviation": 0.05374722539,
|
| 998 |
-
"Rank": 17
|
| 999 |
-
}
|
| 1000 |
-
}
|
| 1001 |
-
},
|
| 1002 |
-
{
|
| 1003 |
-
"config": {
|
| 1004 |
-
"model_name": "claude-2.1",
|
| 1005 |
-
"organization": "Anthropic",
|
| 1006 |
-
"license": "Proprietary",
|
| 1007 |
-
"knowledge_cutoff": "Unknown"
|
| 1008 |
-
},
|
| 1009 |
-
"results": {
|
| 1010 |
-
"OVERALL": {
|
| 1011 |
-
"Average Score": 0.35814708,
|
| 1012 |
-
"Standard Deviation": 0.09168134168,
|
| 1013 |
-
"Rank": 36
|
| 1014 |
-
},
|
| 1015 |
-
"Geometry": {
|
| 1016 |
-
"Average Score": 0.62752395,
|
| 1017 |
-
"Standard Deviation": 0.07232659398,
|
| 1018 |
-
"Rank": 16
|
| 1019 |
-
},
|
| 1020 |
-
"Algebra": {
|
| 1021 |
-
"Average Score": 0.508849609,
|
| 1022 |
-
"Standard Deviation": 0.0346897465,
|
| 1023 |
-
"Rank": 26
|
| 1024 |
-
},
|
| 1025 |
-
"Probability": {
|
| 1026 |
-
"Average Score": 0.41477086,
|
| 1027 |
-
"Standard Deviation": 0.05964060239,
|
| 1028 |
-
"Rank": 29
|
| 1029 |
-
},
|
| 1030 |
-
"Logical": {
|
| 1031 |
-
"Average Score": 0.482923674,
|
| 1032 |
-
"Standard Deviation": 0.01989147048,
|
| 1033 |
-
"Rank": 22
|
| 1034 |
-
},
|
| 1035 |
-
"Social": {
|
| 1036 |
-
"Average Score": 0.333804568,
|
| 1037 |
-
"Standard Deviation": 0.03775548253,
|
| 1038 |
-
"Rank": 29
|
| 1039 |
-
}
|
| 1040 |
-
}
|
| 1041 |
-
},
|
| 1042 |
-
{
|
| 1043 |
-
"config": {
|
| 1044 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 1045 |
-
"organization": "Mistral",
|
| 1046 |
-
"license": "Apache 2.0",
|
| 1047 |
-
"knowledge_cutoff": "2023/12"
|
| 1048 |
-
},
|
| 1049 |
-
"results": {
|
| 1050 |
-
"OVERALL": {
|
| 1051 |
-
"Average Score": 0.382659161,
|
| 1052 |
-
"Standard Deviation": 0.07594496929,
|
| 1053 |
-
"Rank": 31
|
| 1054 |
-
},
|
| 1055 |
-
"Geometry": {
|
| 1056 |
-
"Average Score": 0.432216097,
|
| 1057 |
-
"Standard Deviation": 0.04747949254,
|
| 1058 |
-
"Rank": 31
|
| 1059 |
-
},
|
| 1060 |
-
"Algebra": {
|
| 1061 |
-
"Average Score": 0.478314888,
|
| 1062 |
-
"Standard Deviation": 0.01998797419,
|
| 1063 |
-
"Rank": 27
|
| 1064 |
-
},
|
| 1065 |
-
"Probability": {
|
| 1066 |
-
"Average Score": 0.427144725,
|
| 1067 |
-
"Standard Deviation": 0.0590923329,
|
| 1068 |
-
"Rank": 28
|
| 1069 |
-
},
|
| 1070 |
-
"Logical": {
|
| 1071 |
-
"Average Score": 0.340041983,
|
| 1072 |
-
"Standard Deviation": 0.008397574592,
|
| 1073 |
-
"Rank": 28
|
| 1074 |
-
},
|
| 1075 |
-
"Social": {
|
| 1076 |
-
"Average Score": 0.251949622,
|
| 1077 |
-
"Standard Deviation": 0.03346674405,
|
| 1078 |
-
"Rank": 37
|
| 1079 |
-
}
|
| 1080 |
-
}
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"config": {
|
| 1084 |
-
"model_name": "claude-2.0",
|
| 1085 |
-
"organization": "Anthropic",
|
| 1086 |
-
"license": "Proprietary",
|
| 1087 |
-
"knowledge_cutoff": "Unknown"
|
| 1088 |
-
},
|
| 1089 |
-
"results": {
|
| 1090 |
-
"OVERALL": {
|
| 1091 |
-
"Average Score": 0.322718057,
|
| 1092 |
-
"Standard Deviation": 0.08369883584,
|
| 1093 |
-
"Rank": 38
|
| 1094 |
-
},
|
| 1095 |
-
"Geometry": {
|
| 1096 |
-
"Average Score": 0.604141967,
|
| 1097 |
-
"Standard Deviation": 0.05116441826,
|
| 1098 |
-
"Rank": 18
|
| 1099 |
-
},
|
| 1100 |
-
"Algebra": {
|
| 1101 |
-
"Average Score": 0.474350734,
|
| 1102 |
-
"Standard Deviation": 0.01510393066,
|
| 1103 |
-
"Rank": 28
|
| 1104 |
-
},
|
| 1105 |
-
"Probability": {
|
| 1106 |
-
"Average Score": 0.437950412,
|
| 1107 |
-
"Standard Deviation": 0.05985594317,
|
| 1108 |
-
"Rank": 27
|
| 1109 |
-
},
|
| 1110 |
-
"Logical": {
|
| 1111 |
-
"Average Score": 0.445620646,
|
| 1112 |
-
"Standard Deviation": 0.01812614805,
|
| 1113 |
-
"Rank": 24
|
| 1114 |
-
},
|
| 1115 |
-
"Social": {
|
| 1116 |
-
"Average Score": 0.469422836,
|
| 1117 |
-
"Standard Deviation": 0.05999901796,
|
| 1118 |
-
"Rank": 21
|
| 1119 |
-
}
|
| 1120 |
-
}
|
| 1121 |
-
},
|
| 1122 |
-
{
|
| 1123 |
-
"config": {
|
| 1124 |
-
"model_name": "starling-lm-7b-beta",
|
| 1125 |
-
"organization": "Nexusflow",
|
| 1126 |
-
"license": "Apache-2.0",
|
| 1127 |
-
"knowledge_cutoff": "2024/03"
|
| 1128 |
-
},
|
| 1129 |
-
"results": {
|
| 1130 |
-
"OVERALL": {
|
| 1131 |
-
"Average Score": 0.479391856,
|
| 1132 |
-
"Standard Deviation": 0.04199990887,
|
| 1133 |
-
"Rank": 22
|
| 1134 |
-
},
|
| 1135 |
-
"Geometry": {
|
| 1136 |
-
"Average Score": 0.446654388,
|
| 1137 |
-
"Standard Deviation": 0.05637864999,
|
| 1138 |
-
"Rank": 30
|
| 1139 |
-
},
|
| 1140 |
-
"Algebra": {
|
| 1141 |
-
"Average Score": 0.473952749,
|
| 1142 |
-
"Standard Deviation": 0.01584301288,
|
| 1143 |
-
"Rank": 29
|
| 1144 |
-
},
|
| 1145 |
-
"Probability": {
|
| 1146 |
-
"Average Score": 0.395197837,
|
| 1147 |
-
"Standard Deviation": 0.05814798892,
|
| 1148 |
-
"Rank": 31
|
| 1149 |
-
},
|
| 1150 |
-
"Logical": {
|
| 1151 |
-
"Average Score": 0.39927199,
|
| 1152 |
-
"Standard Deviation": 0.02125277518,
|
| 1153 |
-
"Rank": 26
|
| 1154 |
-
},
|
| 1155 |
-
"Social": {
|
| 1156 |
-
"Average Score": 0.380021662,
|
| 1157 |
-
"Standard Deviation": 0.04622452748,
|
| 1158 |
-
"Rank": 27
|
| 1159 |
-
}
|
| 1160 |
-
}
|
| 1161 |
-
},
|
| 1162 |
-
{
|
| 1163 |
-
"config": {
|
| 1164 |
-
"model_name": "gemini-1.0-pro-001",
|
| 1165 |
-
"organization": "Google",
|
| 1166 |
-
"license": "Proprietary",
|
| 1167 |
-
"knowledge_cutoff": "2023/04"
|
| 1168 |
-
},
|
| 1169 |
-
"results": {
|
| 1170 |
-
"OVERALL": {
|
| 1171 |
-
"Average Score": 0.449040654,
|
| 1172 |
-
"Standard Deviation": 0.0450610177,
|
| 1173 |
-
"Rank": 25
|
| 1174 |
-
},
|
| 1175 |
-
"Geometry": {
|
| 1176 |
-
"Average Score": 0.578347959,
|
| 1177 |
-
"Standard Deviation": 0.04242873607,
|
| 1178 |
-
"Rank": 21
|
| 1179 |
-
},
|
| 1180 |
-
"Algebra": {
|
| 1181 |
-
"Average Score": 0.462417786,
|
| 1182 |
-
"Standard Deviation": 0.01668313635,
|
| 1183 |
-
"Rank": 30
|
| 1184 |
-
},
|
| 1185 |
-
"Probability": {
|
| 1186 |
-
"Average Score": 0.289836324,
|
| 1187 |
-
"Standard Deviation": 0.05739831115,
|
| 1188 |
-
"Rank": 39
|
| 1189 |
-
},
|
| 1190 |
-
"Logical": {
|
| 1191 |
-
"Average Score": 0.191140355,
|
| 1192 |
-
"Standard Deviation": 0.03394652499,
|
| 1193 |
-
"Rank": 41
|
| 1194 |
-
},
|
| 1195 |
-
"Social": {
|
| 1196 |
-
"Average Score": 0.130790863,
|
| 1197 |
-
"Standard Deviation": 0.02800188173,
|
| 1198 |
-
"Rank": 47
|
| 1199 |
-
}
|
| 1200 |
-
}
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"config": {
|
| 1204 |
-
"model_name": "openchat-3.5-0106",
|
| 1205 |
-
"organization": "OpenChat",
|
| 1206 |
-
"license": "Apache-2.0",
|
| 1207 |
-
"knowledge_cutoff": "2024/01"
|
| 1208 |
-
},
|
| 1209 |
-
"results": {
|
| 1210 |
-
"OVERALL": {
|
| 1211 |
-
"Average Score": 0.363929888,
|
| 1212 |
-
"Standard Deviation": 0.08602347145,
|
| 1213 |
-
"Rank": 34
|
| 1214 |
-
},
|
| 1215 |
-
"Geometry": {
|
| 1216 |
-
"Average Score": 0.38715246,
|
| 1217 |
-
"Standard Deviation": 0.03701851946,
|
| 1218 |
-
"Rank": 34
|
| 1219 |
-
},
|
| 1220 |
-
"Algebra": {
|
| 1221 |
-
"Average Score": 0.441233712,
|
| 1222 |
-
"Standard Deviation": 0.01135753754,
|
| 1223 |
-
"Rank": 31
|
| 1224 |
-
},
|
| 1225 |
-
"Probability": {
|
| 1226 |
-
"Average Score": 0.38802618,
|
| 1227 |
-
"Standard Deviation": 0.05663879714,
|
| 1228 |
-
"Rank": 32
|
| 1229 |
-
},
|
| 1230 |
-
"Logical": {
|
| 1231 |
-
"Average Score": 0.336754383,
|
| 1232 |
-
"Standard Deviation": 0.01608478079,
|
| 1233 |
-
"Rank": 29
|
| 1234 |
-
},
|
| 1235 |
-
"Social": {
|
| 1236 |
-
"Average Score": 0.250891608,
|
| 1237 |
-
"Standard Deviation": 0.03253769914,
|
| 1238 |
-
"Rank": 38
|
| 1239 |
-
}
|
| 1240 |
-
}
|
| 1241 |
-
},
|
| 1242 |
-
{
|
| 1243 |
-
"config": {
|
| 1244 |
-
"model_name": "openchat-3.5",
|
| 1245 |
-
"organization": "OpenChat",
|
| 1246 |
-
"license": "Apache-2.0",
|
| 1247 |
-
"knowledge_cutoff": "2023/11"
|
| 1248 |
-
},
|
| 1249 |
-
"results": {
|
| 1250 |
-
"OVERALL": {
|
| 1251 |
-
"Average Score": 0.361341296,
|
| 1252 |
-
"Standard Deviation": 0.09034869493,
|
| 1253 |
-
"Rank": 35
|
| 1254 |
-
},
|
| 1255 |
-
"Geometry": {
|
| 1256 |
-
"Average Score": 0.401699069,
|
| 1257 |
-
"Standard Deviation": 0.03410726557,
|
| 1258 |
-
"Rank": 32
|
| 1259 |
-
},
|
| 1260 |
-
"Algebra": {
|
| 1261 |
-
"Average Score": 0.414095336,
|
| 1262 |
-
"Standard Deviation": 0.01881964261,
|
| 1263 |
-
"Rank": 33
|
| 1264 |
-
},
|
| 1265 |
-
"Probability": {
|
| 1266 |
-
"Average Score": 0.349601002,
|
| 1267 |
-
"Standard Deviation": 0.05077455539,
|
| 1268 |
-
"Rank": 34
|
| 1269 |
-
},
|
| 1270 |
-
"Logical": {
|
| 1271 |
-
"Average Score": 0.331069242,
|
| 1272 |
-
"Standard Deviation": 0.02180827173,
|
| 1273 |
-
"Rank": 31
|
| 1274 |
-
},
|
| 1275 |
-
"Social": {
|
| 1276 |
-
"Average Score": 0.319991655,
|
| 1277 |
-
"Standard Deviation": 0.04502478724,
|
| 1278 |
-
"Rank": 31
|
| 1279 |
-
}
|
| 1280 |
-
}
|
| 1281 |
-
},
|
| 1282 |
-
{
|
| 1283 |
-
"config": {
|
| 1284 |
-
"model_name": "command-r-(08-2024)",
|
| 1285 |
-
"organization": "Cohere",
|
| 1286 |
-
"license": "CC-BY-NC-4.0",
|
| 1287 |
-
"knowledge_cutoff": "2024/08"
|
| 1288 |
-
},
|
| 1289 |
-
"results": {
|
| 1290 |
-
"OVERALL": {
|
| 1291 |
-
"Average Score": 0.427605298,
|
| 1292 |
-
"Standard Deviation": 0.01747449163,
|
| 1293 |
-
"Rank": 26
|
| 1294 |
-
},
|
| 1295 |
-
"Geometry": {
|
| 1296 |
-
"Average Score": 0.448300727,
|
| 1297 |
-
"Standard Deviation": 0.04996362328,
|
| 1298 |
-
"Rank": 29
|
| 1299 |
-
},
|
| 1300 |
-
"Algebra": {
|
| 1301 |
-
"Average Score": 0.417519167,
|
| 1302 |
-
"Standard Deviation": 0.01822196902,
|
| 1303 |
-
"Rank": 32
|
| 1304 |
-
},
|
| 1305 |
-
"Probability": {
|
| 1306 |
-
"Average Score": 0.366336281,
|
| 1307 |
-
"Standard Deviation": 0.04716826942,
|
| 1308 |
-
"Rank": 33
|
| 1309 |
-
},
|
| 1310 |
-
"Logical": {
|
| 1311 |
-
"Average Score": 0.214657906,
|
| 1312 |
-
"Standard Deviation": 0.03003579835,
|
| 1313 |
-
"Rank": 38
|
| 1314 |
-
},
|
| 1315 |
-
"Social": {
|
| 1316 |
-
"Average Score": 0.276088379,
|
| 1317 |
-
"Standard Deviation": 0.03295234688,
|
| 1318 |
-
"Rank": 34
|
| 1319 |
-
}
|
| 1320 |
-
}
|
| 1321 |
-
},
|
| 1322 |
-
{
|
| 1323 |
-
"config": {
|
| 1324 |
-
"model_name": "gemma-1.1-7b-it",
|
| 1325 |
-
"organization": "Google",
|
| 1326 |
-
"license": "Gemma License",
|
| 1327 |
-
"knowledge_cutoff": "2024/02"
|
| 1328 |
-
},
|
| 1329 |
-
"results": {
|
| 1330 |
-
"OVERALL": {
|
| 1331 |
-
"Average Score": 0.339506922,
|
| 1332 |
-
"Standard Deviation": 0.1066279108,
|
| 1333 |
-
"Rank": 37
|
| 1334 |
-
},
|
| 1335 |
-
"Geometry": {
|
| 1336 |
-
"Average Score": 0.324170977,
|
| 1337 |
-
"Standard Deviation": 0.04668553765,
|
| 1338 |
-
"Rank": 37
|
| 1339 |
-
},
|
| 1340 |
-
"Algebra": {
|
| 1341 |
-
"Average Score": 0.398684697,
|
| 1342 |
-
"Standard Deviation": 0.01982398259,
|
| 1343 |
-
"Rank": 34
|
| 1344 |
-
},
|
| 1345 |
-
"Probability": {
|
| 1346 |
-
"Average Score": 0.293253175,
|
| 1347 |
-
"Standard Deviation": 0.05126192191,
|
| 1348 |
-
"Rank": 38
|
| 1349 |
-
},
|
| 1350 |
-
"Logical": {
|
| 1351 |
-
"Average Score": 0.317750796,
|
| 1352 |
-
"Standard Deviation": 0.01101933543,
|
| 1353 |
-
"Rank": 32
|
| 1354 |
-
},
|
| 1355 |
-
"Social": {
|
| 1356 |
-
"Average Score": 0.179073276,
|
| 1357 |
-
"Standard Deviation": 0.02009658805,
|
| 1358 |
-
"Rank": 43
|
| 1359 |
-
}
|
| 1360 |
-
}
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"config": {
|
| 1364 |
-
"model_name": "llama3-8b-instruct",
|
| 1365 |
-
"organization": "Meta",
|
| 1366 |
-
"license": "Llama 3 Community",
|
| 1367 |
-
"knowledge_cutoff": "2023/03"
|
| 1368 |
-
},
|
| 1369 |
-
"results": {
|
| 1370 |
-
"OVERALL": {
|
| 1371 |
-
"Average Score": 0.367722676,
|
| 1372 |
-
"Standard Deviation": 0.1071368221,
|
| 1373 |
-
"Rank": 32
|
| 1374 |
-
},
|
| 1375 |
-
"Geometry": {
|
| 1376 |
-
"Average Score": 0.367143758,
|
| 1377 |
-
"Standard Deviation": 0.04363680358,
|
| 1378 |
-
"Rank": 35
|
| 1379 |
-
},
|
| 1380 |
-
"Algebra": {
|
| 1381 |
-
"Average Score": 0.391480973,
|
| 1382 |
-
"Standard Deviation": 0.02757445266,
|
| 1383 |
-
"Rank": 35
|
| 1384 |
-
},
|
| 1385 |
-
"Probability": {
|
| 1386 |
-
"Average Score": 0.317616445,
|
| 1387 |
-
"Standard Deviation": 0.04300430361,
|
| 1388 |
-
"Rank": 37
|
| 1389 |
-
},
|
| 1390 |
-
"Logical": {
|
| 1391 |
-
"Average Score": 0.461607495,
|
| 1392 |
-
"Standard Deviation": 0.02185028842,
|
| 1393 |
-
"Rank": 23
|
| 1394 |
-
},
|
| 1395 |
-
"Social": {
|
| 1396 |
-
"Average Score": 0.336373622,
|
| 1397 |
-
"Standard Deviation": 0.05762408512,
|
| 1398 |
-
"Rank": 28
|
| 1399 |
-
}
|
| 1400 |
-
}
|
| 1401 |
-
},
|
| 1402 |
-
{
|
| 1403 |
-
"config": {
|
| 1404 |
-
"model_name": "gemma-2-2b-it",
|
| 1405 |
-
"organization": "Google",
|
| 1406 |
-
"license": "Gemma License",
|
| 1407 |
-
"knowledge_cutoff": "2024/07"
|
| 1408 |
-
},
|
| 1409 |
-
"results": {
|
| 1410 |
-
"OVERALL": {
|
| 1411 |
-
"Average Score": 0.502167612,
|
| 1412 |
-
"Standard Deviation": 0.04389786763,
|
| 1413 |
-
"Rank": 20
|
| 1414 |
-
},
|
| 1415 |
-
"Geometry": {
|
| 1416 |
-
"Average Score": 0.395006676,
|
| 1417 |
-
"Standard Deviation": 0.05882607713,
|
| 1418 |
-
"Rank": 33
|
| 1419 |
-
},
|
| 1420 |
-
"Algebra": {
|
| 1421 |
-
"Average Score": 0.379391887,
|
| 1422 |
-
"Standard Deviation": 0.01722410785,
|
| 1423 |
-
"Rank": 36
|
| 1424 |
-
},
|
| 1425 |
-
"Probability": {
|
| 1426 |
-
"Average Score": 0.331231097,
|
| 1427 |
-
"Standard Deviation": 0.05392499987,
|
| 1428 |
-
"Rank": 36
|
| 1429 |
-
},
|
| 1430 |
-
"Logical": {
|
| 1431 |
-
"Average Score": 0.367687789,
|
| 1432 |
-
"Standard Deviation": 0.02547968808,
|
| 1433 |
-
"Rank": 27
|
| 1434 |
-
},
|
| 1435 |
-
"Social": {
|
| 1436 |
-
"Average Score": 0.393482094,
|
| 1437 |
-
"Standard Deviation": 0.06450214024,
|
| 1438 |
-
"Rank": 25
|
| 1439 |
-
}
|
| 1440 |
-
}
|
| 1441 |
-
},
|
| 1442 |
-
{
|
| 1443 |
-
"config": {
|
| 1444 |
-
"model_name": "starling-lm-7b-alpha",
|
| 1445 |
-
"organization": "Nexusflow",
|
| 1446 |
-
"license": "Apache-2.0",
|
| 1447 |
-
"knowledge_cutoff": "2023/11"
|
| 1448 |
-
},
|
| 1449 |
-
"results": {
|
| 1450 |
-
"OVERALL": {
|
| 1451 |
-
"Average Score": 0.366628765,
|
| 1452 |
-
"Standard Deviation": 0.08405492929,
|
| 1453 |
-
"Rank": 33
|
| 1454 |
-
},
|
| 1455 |
-
"Geometry": {
|
| 1456 |
-
"Average Score": 0.336782578,
|
| 1457 |
-
"Standard Deviation": 0.04069449132,
|
| 1458 |
-
"Rank": 36
|
| 1459 |
-
},
|
| 1460 |
-
"Algebra": {
|
| 1461 |
-
"Average Score": 0.371551932,
|
| 1462 |
-
"Standard Deviation": 0.03367241745,
|
| 1463 |
-
"Rank": 37
|
| 1464 |
-
},
|
| 1465 |
-
"Probability": {
|
| 1466 |
-
"Average Score": 0.331472505,
|
| 1467 |
-
"Standard Deviation": 0.04833324282,
|
| 1468 |
-
"Rank": 35
|
| 1469 |
-
},
|
| 1470 |
-
"Logical": {
|
| 1471 |
-
"Average Score": 0.260869624,
|
| 1472 |
-
"Standard Deviation": 0.03562735237,
|
| 1473 |
-
"Rank": 36
|
| 1474 |
-
},
|
| 1475 |
-
"Social": {
|
| 1476 |
-
"Average Score": 0.271975534,
|
| 1477 |
-
"Standard Deviation": 0.04266753408,
|
| 1478 |
-
"Rank": 35
|
| 1479 |
-
}
|
| 1480 |
-
}
|
| 1481 |
-
},
|
| 1482 |
-
{
|
| 1483 |
-
"config": {
|
| 1484 |
-
"model_name": "qwen1.5-4b-chat",
|
| 1485 |
-
"organization": "Alibaba",
|
| 1486 |
-
"license": "Qianwen LICENSE",
|
| 1487 |
-
"knowledge_cutoff": "2024/02"
|
| 1488 |
-
},
|
| 1489 |
-
"results": {
|
| 1490 |
-
"OVERALL": {
|
| 1491 |
-
"Average Score": 0.111876411,
|
| 1492 |
-
"Standard Deviation": 0.04241022785,
|
| 1493 |
-
"Rank": 49
|
| 1494 |
-
},
|
| 1495 |
-
"Geometry": {
|
| 1496 |
-
"Average Score": 0.215834522,
|
| 1497 |
-
"Standard Deviation": 0.0363766363,
|
| 1498 |
-
"Rank": 41
|
| 1499 |
-
},
|
| 1500 |
-
"Algebra": {
|
| 1501 |
-
"Average Score": 0.305589811,
|
| 1502 |
-
"Standard Deviation": 0.02354198912,
|
| 1503 |
-
"Rank": 38
|
| 1504 |
-
},
|
| 1505 |
-
"Probability": {
|
| 1506 |
-
"Average Score": 0.149365327,
|
| 1507 |
-
"Standard Deviation": 0.03489672675,
|
| 1508 |
-
"Rank": 45
|
| 1509 |
-
},
|
| 1510 |
-
"Logical": {
|
| 1511 |
-
"Average Score": 0.116210168,
|
| 1512 |
-
"Standard Deviation": 0.005927966496,
|
| 1513 |
-
"Rank": 47
|
| 1514 |
-
},
|
| 1515 |
-
"Social": {
|
| 1516 |
-
"Average Score": 0.18195615,
|
| 1517 |
-
"Standard Deviation": 0.02269805277,
|
| 1518 |
-
"Rank": 42
|
| 1519 |
-
}
|
| 1520 |
-
}
|
| 1521 |
-
},
|
| 1522 |
-
{
|
| 1523 |
-
"config": {
|
| 1524 |
-
"model_name": "command-r-(04-2024)",
|
| 1525 |
-
"organization": "Cohere",
|
| 1526 |
-
"license": "CC-BY-NC-4.0",
|
| 1527 |
-
"knowledge_cutoff": "2024/04"
|
| 1528 |
-
},
|
| 1529 |
-
"results": {
|
| 1530 |
-
"OVERALL": {
|
| 1531 |
-
"Average Score": 0.388783887,
|
| 1532 |
-
"Standard Deviation": 0.07417186783,
|
| 1533 |
-
"Rank": 30
|
| 1534 |
-
},
|
| 1535 |
-
"Geometry": {
|
| 1536 |
-
"Average Score": 0.300416698,
|
| 1537 |
-
"Standard Deviation": 0.03485612736,
|
| 1538 |
-
"Rank": 38
|
| 1539 |
-
},
|
| 1540 |
-
"Algebra": {
|
| 1541 |
-
"Average Score": 0.293120231,
|
| 1542 |
-
"Standard Deviation": 0.032926484,
|
| 1543 |
-
"Rank": 39
|
| 1544 |
-
},
|
| 1545 |
-
"Probability": {
|
| 1546 |
-
"Average Score": 0.281271304,
|
| 1547 |
-
"Standard Deviation": 0.05697149867,
|
| 1548 |
-
"Rank": 40
|
| 1549 |
-
},
|
| 1550 |
-
"Logical": {
|
| 1551 |
-
"Average Score": 0.276189906,
|
| 1552 |
-
"Standard Deviation": 0.03562914754,
|
| 1553 |
-
"Rank": 34
|
| 1554 |
-
},
|
| 1555 |
-
"Social": {
|
| 1556 |
-
"Average Score": 0.283882949,
|
| 1557 |
-
"Standard Deviation": 0.03336901148,
|
| 1558 |
-
"Rank": 33
|
| 1559 |
-
}
|
| 1560 |
-
}
|
| 1561 |
-
},
|
| 1562 |
-
{
|
| 1563 |
-
"config": {
|
| 1564 |
-
"model_name": "vicuna-33b",
|
| 1565 |
-
"organization": "LMSYS",
|
| 1566 |
-
"license": "Non-commercial",
|
| 1567 |
-
"knowledge_cutoff": "2023/08"
|
| 1568 |
-
},
|
| 1569 |
-
"results": {
|
| 1570 |
-
"OVERALL": {
|
| 1571 |
-
"Average Score": 0.316543555,
|
| 1572 |
-
"Standard Deviation": 0.08922095647,
|
| 1573 |
-
"Rank": 39
|
| 1574 |
-
},
|
| 1575 |
-
"Geometry": {
|
| 1576 |
-
"Average Score": 0.208284679,
|
| 1577 |
-
"Standard Deviation": 0.03937771461,
|
| 1578 |
-
"Rank": 42
|
| 1579 |
-
},
|
| 1580 |
-
"Algebra": {
|
| 1581 |
-
"Average Score": 0.248994048,
|
| 1582 |
-
"Standard Deviation": 0.02668175054,
|
| 1583 |
-
"Rank": 41
|
| 1584 |
-
},
|
| 1585 |
-
"Probability": {
|
| 1586 |
-
"Average Score": 0.222313995,
|
| 1587 |
-
"Standard Deviation": 0.03978859759,
|
| 1588 |
-
"Rank": 43
|
| 1589 |
-
},
|
| 1590 |
-
"Logical": {
|
| 1591 |
-
"Average Score": 0.180291222,
|
| 1592 |
-
"Standard Deviation": 0.021886267,
|
| 1593 |
-
"Rank": 42
|
| 1594 |
-
},
|
| 1595 |
-
"Social": {
|
| 1596 |
-
"Average Score": 0.257623798,
|
| 1597 |
-
"Standard Deviation": 0.02653724437,
|
| 1598 |
-
"Rank": 36
|
| 1599 |
-
}
|
| 1600 |
-
}
|
| 1601 |
-
},
|
| 1602 |
-
{
|
| 1603 |
-
"config": {
|
| 1604 |
-
"model_name": "gemma-7b-it",
|
| 1605 |
-
"organization": "Google",
|
| 1606 |
-
"license": "Gemma License",
|
| 1607 |
-
"knowledge_cutoff": "2024/02"
|
| 1608 |
-
},
|
| 1609 |
-
"results": {
|
| 1610 |
-
"OVERALL": {
|
| 1611 |
-
"Average Score": 0.285077558,
|
| 1612 |
-
"Standard Deviation": 0.08871758453,
|
| 1613 |
-
"Rank": 41
|
| 1614 |
-
},
|
| 1615 |
-
"Geometry": {
|
| 1616 |
-
"Average Score": 0.244791417,
|
| 1617 |
-
"Standard Deviation": 0.0289612078,
|
| 1618 |
-
"Rank": 39
|
| 1619 |
-
},
|
| 1620 |
-
"Algebra": {
|
| 1621 |
-
"Average Score": 0.250614794,
|
| 1622 |
-
"Standard Deviation": 0.01991678295,
|
| 1623 |
-
"Rank": 40
|
| 1624 |
-
},
|
| 1625 |
-
"Probability": {
|
| 1626 |
-
"Average Score": 0.174313053,
|
| 1627 |
-
"Standard Deviation": 0.03765424728,
|
| 1628 |
-
"Rank": 44
|
| 1629 |
-
},
|
| 1630 |
-
"Logical": {
|
| 1631 |
-
"Average Score": 0.197505536,
|
| 1632 |
-
"Standard Deviation": 0.02050298885,
|
| 1633 |
-
"Rank": 39
|
| 1634 |
-
},
|
| 1635 |
-
"Social": {
|
| 1636 |
-
"Average Score": 0.202138025,
|
| 1637 |
-
"Standard Deviation": 0.02098346639,
|
| 1638 |
-
"Rank": 41
|
| 1639 |
-
}
|
| 1640 |
-
}
|
| 1641 |
-
},
|
| 1642 |
-
{
|
| 1643 |
-
"config": {
|
| 1644 |
-
"model_name": "mistral-7b-instruct-2",
|
| 1645 |
-
"organization": "Mistral",
|
| 1646 |
-
"license": "Apache 2.0",
|
| 1647 |
-
"knowledge_cutoff": "2023/12"
|
| 1648 |
-
},
|
| 1649 |
-
"results": {
|
| 1650 |
-
"OVERALL": {
|
| 1651 |
-
"Average Score": 0.427513868,
|
| 1652 |
-
"Standard Deviation": 0.05553921135,
|
| 1653 |
-
"Rank": 27
|
| 1654 |
-
},
|
| 1655 |
-
"Geometry": {
|
| 1656 |
-
"Average Score": 0.216402626,
|
| 1657 |
-
"Standard Deviation": 0.03338414918,
|
| 1658 |
-
"Rank": 40
|
| 1659 |
-
},
|
| 1660 |
-
"Algebra": {
|
| 1661 |
-
"Average Score": 0.233777838,
|
| 1662 |
-
"Standard Deviation": 0.0155226054,
|
| 1663 |
-
"Rank": 42
|
| 1664 |
-
},
|
| 1665 |
-
"Probability": {
|
| 1666 |
-
"Average Score": 0.25118175,
|
| 1667 |
-
"Standard Deviation": 0.04065514593,
|
| 1668 |
-
"Rank": 41
|
| 1669 |
-
},
|
| 1670 |
-
"Logical": {
|
| 1671 |
-
"Average Score": 0.224469136,
|
| 1672 |
-
"Standard Deviation": 0.03404706752,
|
| 1673 |
-
"Rank": 37
|
| 1674 |
-
},
|
| 1675 |
-
"Social": {
|
| 1676 |
-
"Average Score": 0.209386782,
|
| 1677 |
-
"Standard Deviation": 0.02738569921,
|
| 1678 |
-
"Rank": 40
|
| 1679 |
-
}
|
| 1680 |
-
}
|
| 1681 |
-
},
|
| 1682 |
-
{
|
| 1683 |
-
"config": {
|
| 1684 |
-
"model_name": "mistral-7b-instruct-1",
|
| 1685 |
-
"organization": "Mistral",
|
| 1686 |
-
"license": "Apache 2.0",
|
| 1687 |
-
"knowledge_cutoff": "2023/12"
|
| 1688 |
-
},
|
| 1689 |
-
"results": {
|
| 1690 |
-
"OVERALL": {
|
| 1691 |
-
"Average Score": 0.23016314,
|
| 1692 |
-
"Standard Deviation": 0.07137625271,
|
| 1693 |
-
"Rank": 46
|
| 1694 |
-
},
|
| 1695 |
-
"Geometry": {
|
| 1696 |
-
"Average Score": 0.161799938,
|
| 1697 |
-
"Standard Deviation": 0.03595278559,
|
| 1698 |
-
"Rank": 46
|
| 1699 |
-
},
|
| 1700 |
-
"Algebra": {
|
| 1701 |
-
"Average Score": 0.210341624,
|
| 1702 |
-
"Standard Deviation": 0.01736539119,
|
| 1703 |
-
"Rank": 43
|
| 1704 |
-
},
|
| 1705 |
-
"Probability": {
|
| 1706 |
-
"Average Score": 0.238417922,
|
| 1707 |
-
"Standard Deviation": 0.03744211933,
|
| 1708 |
-
"Rank": 42
|
| 1709 |
-
},
|
| 1710 |
-
"Logical": {
|
| 1711 |
-
"Average Score": 0.142636601,
|
| 1712 |
-
"Standard Deviation": 0.02080406365,
|
| 1713 |
-
"Rank": 46
|
| 1714 |
-
},
|
| 1715 |
-
"Social": {
|
| 1716 |
-
"Average Score": 0.117646827,
|
| 1717 |
-
"Standard Deviation": 0.009321202779,
|
| 1718 |
-
"Rank": 49
|
| 1719 |
-
}
|
| 1720 |
-
}
|
| 1721 |
-
},
|
| 1722 |
-
{
|
| 1723 |
-
"config": {
|
| 1724 |
-
"model_name": "vicuna-13b",
|
| 1725 |
-
"organization": "LMSYS",
|
| 1726 |
-
"license": "Non-commercial",
|
| 1727 |
-
"knowledge_cutoff": "2023/07"
|
| 1728 |
-
},
|
| 1729 |
-
"results": {
|
| 1730 |
-
"OVERALL": {
|
| 1731 |
-
"Average Score": 0.201892849,
|
| 1732 |
-
"Standard Deviation": 0.06021749802,
|
| 1733 |
-
"Rank": 47
|
| 1734 |
-
},
|
| 1735 |
-
"Geometry": {
|
| 1736 |
-
"Average Score": 0.200941928,
|
| 1737 |
-
"Standard Deviation": 0.03366817781,
|
| 1738 |
-
"Rank": 43
|
| 1739 |
-
},
|
| 1740 |
-
"Algebra": {
|
| 1741 |
-
"Average Score": 0.196123323,
|
| 1742 |
-
"Standard Deviation": 0.0135715643,
|
| 1743 |
-
"Rank": 44
|
| 1744 |
-
},
|
| 1745 |
-
"Probability": {
|
| 1746 |
-
"Average Score": 0.141214079,
|
| 1747 |
-
"Standard Deviation": 0.02721328211,
|
| 1748 |
-
"Rank": 46
|
| 1749 |
-
},
|
| 1750 |
-
"Logical": {
|
| 1751 |
-
"Average Score": 0.148598631,
|
| 1752 |
-
"Standard Deviation": 0.02241523892,
|
| 1753 |
-
"Rank": 44
|
| 1754 |
-
},
|
| 1755 |
-
"Social": {
|
| 1756 |
-
"Average Score": 0.124655135,
|
| 1757 |
-
"Standard Deviation": 0.01122382671,
|
| 1758 |
-
"Rank": 48
|
| 1759 |
-
}
|
| 1760 |
-
}
|
| 1761 |
-
},
|
| 1762 |
-
{
|
| 1763 |
-
"config": {
|
| 1764 |
-
"model_name": "zephyr-7b-beta",
|
| 1765 |
-
"organization": "HuggingFace",
|
| 1766 |
-
"license": "MIT",
|
| 1767 |
-
"knowledge_cutoff": "2023/10"
|
| 1768 |
-
},
|
| 1769 |
-
"results": {
|
| 1770 |
-
"OVERALL": {
|
| 1771 |
-
"Average Score": 0.102705119,
|
| 1772 |
-
"Standard Deviation": 0.03683757312,
|
| 1773 |
-
"Rank": 50
|
| 1774 |
-
},
|
| 1775 |
-
"Geometry": {
|
| 1776 |
-
"Average Score": 0.114005544,
|
| 1777 |
-
"Standard Deviation": 0.03144354365,
|
| 1778 |
-
"Rank": 47
|
| 1779 |
-
},
|
| 1780 |
-
"Algebra": {
|
| 1781 |
-
"Average Score": 0.141766633,
|
| 1782 |
-
"Standard Deviation": 0.03179520129,
|
| 1783 |
-
"Rank": 45
|
| 1784 |
-
},
|
| 1785 |
-
"Probability": {
|
| 1786 |
-
"Average Score": 0.089050714,
|
| 1787 |
-
"Standard Deviation": 0.002136754266,
|
| 1788 |
-
"Rank": 49
|
| 1789 |
-
},
|
| 1790 |
-
"Logical": {
|
| 1791 |
-
"Average Score": 0.069520789,
|
| 1792 |
-
"Standard Deviation": 0.004477840857,
|
| 1793 |
-
"Rank": 51
|
| 1794 |
-
},
|
| 1795 |
-
"Social": {
|
| 1796 |
-
"Average Score": 0.0,
|
| 1797 |
-
"Standard Deviation": 0.0,
|
| 1798 |
-
"Rank": 54
|
| 1799 |
-
}
|
| 1800 |
-
}
|
| 1801 |
-
},
|
| 1802 |
-
{
|
| 1803 |
-
"config": {
|
| 1804 |
-
"model_name": "gemma-1.1-2b-it",
|
| 1805 |
-
"organization": "Google",
|
| 1806 |
-
"license": "Gemma License",
|
| 1807 |
-
"knowledge_cutoff": "2024/02"
|
| 1808 |
-
},
|
| 1809 |
-
"results": {
|
| 1810 |
-
"OVERALL": {
|
| 1811 |
-
"Average Score": 0.257700845,
|
| 1812 |
-
"Standard Deviation": 0.07369021445,
|
| 1813 |
-
"Rank": 44
|
| 1814 |
-
},
|
| 1815 |
-
"Geometry": {
|
| 1816 |
-
"Average Score": 0.183974034,
|
| 1817 |
-
"Standard Deviation": 0.0215548886,
|
| 1818 |
-
"Rank": 45
|
| 1819 |
-
},
|
| 1820 |
-
"Algebra": {
|
| 1821 |
-
"Average Score": 0.13422252,
|
| 1822 |
-
"Standard Deviation": 0.01922819511,
|
| 1823 |
-
"Rank": 46
|
| 1824 |
-
},
|
| 1825 |
-
"Probability": {
|
| 1826 |
-
"Average Score": 0.095628657,
|
| 1827 |
-
"Standard Deviation": 0.007536076456,
|
| 1828 |
-
"Rank": 48
|
| 1829 |
-
},
|
| 1830 |
-
"Logical": {
|
| 1831 |
-
"Average Score": 0.094965074,
|
| 1832 |
-
"Standard Deviation": 0.005019175487,
|
| 1833 |
-
"Rank": 49
|
| 1834 |
-
},
|
| 1835 |
-
"Social": {
|
| 1836 |
-
"Average Score": 0.167796727,
|
| 1837 |
-
"Standard Deviation": 0.01666541942,
|
| 1838 |
-
"Rank": 44
|
| 1839 |
-
}
|
| 1840 |
-
}
|
| 1841 |
-
},
|
| 1842 |
-
{
|
| 1843 |
-
"config": {
|
| 1844 |
-
"model_name": "llama2-7b-chat",
|
| 1845 |
-
"organization": "Meta",
|
| 1846 |
-
"license": "Llama 2 Community",
|
| 1847 |
-
"knowledge_cutoff": "2023/07"
|
| 1848 |
-
},
|
| 1849 |
-
"results": {
|
| 1850 |
-
"OVERALL": {
|
| 1851 |
-
"Average Score": 0.260189428,
|
| 1852 |
-
"Standard Deviation": 0.08019299364,
|
| 1853 |
-
"Rank": 43
|
| 1854 |
-
},
|
| 1855 |
-
"Geometry": {
|
| 1856 |
-
"Average Score": 0.087067276,
|
| 1857 |
-
"Standard Deviation": 0.04274343402,
|
| 1858 |
-
"Rank": 48
|
| 1859 |
-
},
|
| 1860 |
-
"Algebra": {
|
| 1861 |
-
"Average Score": 0.12308805,
|
| 1862 |
-
"Standard Deviation": 0.01856053622,
|
| 1863 |
-
"Rank": 47
|
| 1864 |
-
},
|
| 1865 |
-
"Probability": {
|
| 1866 |
-
"Average Score": 0.087515438,
|
| 1867 |
-
"Standard Deviation": 0.006315053573,
|
| 1868 |
-
"Rank": 50
|
| 1869 |
-
},
|
| 1870 |
-
"Logical": {
|
| 1871 |
-
"Average Score": 0.17312827,
|
| 1872 |
-
"Standard Deviation": 0.01867044092,
|
| 1873 |
-
"Rank": 43
|
| 1874 |
-
},
|
| 1875 |
-
"Social": {
|
| 1876 |
-
"Average Score": 0.152905272,
|
| 1877 |
-
"Standard Deviation": 0.007166957097,
|
| 1878 |
-
"Rank": 45
|
| 1879 |
-
}
|
| 1880 |
-
}
|
| 1881 |
-
},
|
| 1882 |
-
{
|
| 1883 |
-
"config": {
|
| 1884 |
-
"model_name": "gemma-2b-it",
|
| 1885 |
-
"organization": "Google",
|
| 1886 |
-
"license": "Gemma License",
|
| 1887 |
-
"knowledge_cutoff": "2024/02"
|
| 1888 |
-
},
|
| 1889 |
-
"results": {
|
| 1890 |
-
"OVERALL": {
|
| 1891 |
-
"Average Score": 0.234172069,
|
| 1892 |
-
"Standard Deviation": 0.06522685718,
|
| 1893 |
-
"Rank": 45
|
| 1894 |
-
},
|
| 1895 |
-
"Geometry": {
|
| 1896 |
-
"Average Score": 0.198571153,
|
| 1897 |
-
"Standard Deviation": 0.01699161031,
|
| 1898 |
-
"Rank": 44
|
| 1899 |
-
},
|
| 1900 |
-
"Algebra": {
|
| 1901 |
-
"Average Score": 0.109883009,
|
| 1902 |
-
"Standard Deviation": 0.01520005833,
|
| 1903 |
-
"Rank": 48
|
| 1904 |
-
},
|
| 1905 |
-
"Probability": {
|
| 1906 |
-
"Average Score": 0.06467432,
|
| 1907 |
-
"Standard Deviation": 0.002117497231,
|
| 1908 |
-
"Rank": 52
|
| 1909 |
-
},
|
| 1910 |
-
"Logical": {
|
| 1911 |
-
"Average Score": 0.039624492,
|
| 1912 |
-
"Standard Deviation": 0.007606972686,
|
| 1913 |
-
"Rank": 52
|
| 1914 |
-
},
|
| 1915 |
-
"Social": {
|
| 1916 |
-
"Average Score": 0.087452913,
|
| 1917 |
-
"Standard Deviation": 0.008170146562,
|
| 1918 |
-
"Rank": 52
|
| 1919 |
-
}
|
| 1920 |
-
}
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"config": {
|
| 1924 |
-
"model_name": "llama2-13b-chat",
|
| 1925 |
-
"organization": "Meta",
|
| 1926 |
-
"license": "Llama 2 Community",
|
| 1927 |
-
"knowledge_cutoff": "2023/07"
|
| 1928 |
-
},
|
| 1929 |
-
"results": {
|
| 1930 |
-
"OVERALL": {
|
| 1931 |
-
"Average Score": 0.263305684,
|
| 1932 |
-
"Standard Deviation": 0.07283640689,
|
| 1933 |
-
"Rank": 42
|
| 1934 |
-
},
|
| 1935 |
-
"Geometry": {
|
| 1936 |
-
"Average Score": 0.072729954,
|
| 1937 |
-
"Standard Deviation": 0.02315988261,
|
| 1938 |
-
"Rank": 50
|
| 1939 |
-
},
|
| 1940 |
-
"Algebra": {
|
| 1941 |
-
"Average Score": 0.080371692,
|
| 1942 |
-
"Standard Deviation": 0.01277569453,
|
| 1943 |
-
"Rank": 49
|
| 1944 |
-
},
|
| 1945 |
-
"Probability": {
|
| 1946 |
-
"Average Score": 0.117757344,
|
| 1947 |
-
"Standard Deviation": 0.02418619619,
|
| 1948 |
-
"Rank": 47
|
| 1949 |
-
},
|
| 1950 |
-
"Logical": {
|
| 1951 |
-
"Average Score": 0.193149889,
|
| 1952 |
-
"Standard Deviation": 0.01776690764,
|
| 1953 |
-
"Rank": 40
|
| 1954 |
-
},
|
| 1955 |
-
"Social": {
|
| 1956 |
-
"Average Score": 0.149125922,
|
| 1957 |
-
"Standard Deviation": 0.01157416827,
|
| 1958 |
-
"Rank": 46
|
| 1959 |
-
}
|
| 1960 |
-
}
|
| 1961 |
-
},
|
| 1962 |
-
{
|
| 1963 |
-
"config": {
|
| 1964 |
-
"model_name": "vicuna-7b",
|
| 1965 |
-
"organization": "LMSYS",
|
| 1966 |
-
"license": "Non-commercial",
|
| 1967 |
-
"knowledge_cutoff": "2023/07"
|
| 1968 |
-
},
|
| 1969 |
-
"results": {
|
| 1970 |
-
"OVERALL": {
|
| 1971 |
-
"Average Score": 0.198839786,
|
| 1972 |
-
"Standard Deviation": 0.05725381576,
|
| 1973 |
-
"Rank": 48
|
| 1974 |
-
},
|
| 1975 |
-
"Geometry": {
|
| 1976 |
-
"Average Score": 0.083457058,
|
| 1977 |
-
"Standard Deviation": 0.02520989111,
|
| 1978 |
-
"Rank": 49
|
| 1979 |
-
},
|
| 1980 |
-
"Algebra": {
|
| 1981 |
-
"Average Score": 0.070883882,
|
| 1982 |
-
"Standard Deviation": 0.007315853253,
|
| 1983 |
-
"Rank": 50
|
| 1984 |
-
},
|
| 1985 |
-
"Probability": {
|
| 1986 |
-
"Average Score": 0.080987673,
|
| 1987 |
-
"Standard Deviation": 0.005474288861,
|
| 1988 |
-
"Rank": 51
|
| 1989 |
-
},
|
| 1990 |
-
"Logical": {
|
| 1991 |
-
"Average Score": 0.100065588,
|
| 1992 |
-
"Standard Deviation": 0.003561886452,
|
| 1993 |
-
"Rank": 48
|
| 1994 |
-
},
|
| 1995 |
-
"Social": {
|
| 1996 |
-
"Average Score": 0.111076414,
|
| 1997 |
-
"Standard Deviation": 0.004805626512,
|
| 1998 |
-
"Rank": 50
|
| 1999 |
-
}
|
| 2000 |
-
}
|
| 2001 |
-
},
|
| 2002 |
-
{
|
| 2003 |
-
"config": {
|
| 2004 |
-
"model_name": "koala-13b",
|
| 2005 |
-
"organization": "UC Berkeley",
|
| 2006 |
-
"license": "Non-commercial",
|
| 2007 |
-
"knowledge_cutoff": "2023/04"
|
| 2008 |
-
},
|
| 2009 |
-
"results": {
|
| 2010 |
-
"OVERALL": {
|
| 2011 |
-
"Average Score": 0.09387188,
|
| 2012 |
-
"Standard Deviation": 0.02642167489,
|
| 2013 |
-
"Rank": 51
|
| 2014 |
-
},
|
| 2015 |
-
"Geometry": {
|
| 2016 |
-
"Average Score": 0.017374001,
|
| 2017 |
-
"Standard Deviation": 0.01747053557,
|
| 2018 |
-
"Rank": 51
|
| 2019 |
-
},
|
| 2020 |
-
"Algebra": {
|
| 2021 |
-
"Average Score": 0.018129197,
|
| 2022 |
-
"Standard Deviation": 0.01054371383,
|
| 2023 |
-
"Rank": 51
|
| 2024 |
-
},
|
| 2025 |
-
"Probability": {
|
| 2026 |
-
"Average Score": 0.043654362,
|
| 2027 |
-
"Standard Deviation": 0.004288231886,
|
| 2028 |
-
"Rank": 53
|
| 2029 |
-
},
|
| 2030 |
-
"Logical": {
|
| 2031 |
-
"Average Score": 0.074694053,
|
| 2032 |
-
"Standard Deviation": 0.002674646998,
|
| 2033 |
-
"Rank": 50
|
| 2034 |
-
},
|
| 2035 |
-
"Social": {
|
| 2036 |
-
"Average Score": 0.096983835,
|
| 2037 |
-
"Standard Deviation": 0.007847059783,
|
| 2038 |
-
"Rank": 51
|
| 2039 |
-
}
|
| 2040 |
-
}
|
| 2041 |
-
},
|
| 2042 |
-
{
|
| 2043 |
-
"config": {
|
| 2044 |
-
"model_name": "openassistant-pythia-12b",
|
| 2045 |
-
"organization": "OpenAssistant",
|
| 2046 |
-
"license": "Non-commercial",
|
| 2047 |
-
"knowledge_cutoff": "2023/04"
|
| 2048 |
-
},
|
| 2049 |
-
"results": {
|
| 2050 |
-
"OVERALL": {
|
| 2051 |
-
"Average Score": 0.0,
|
| 2052 |
-
"Standard Deviation": 0.0,
|
| 2053 |
-
"Rank": 52
|
| 2054 |
-
},
|
| 2055 |
-
"Geometry": {
|
| 2056 |
-
"Average Score": 0.0,
|
| 2057 |
-
"Standard Deviation": 0.0,
|
| 2058 |
-
"Rank": 52
|
| 2059 |
-
},
|
| 2060 |
-
"Algebra": {
|
| 2061 |
-
"Average Score": 0.0,
|
| 2062 |
-
"Standard Deviation": 0.0,
|
| 2063 |
-
"Rank": 52
|
| 2064 |
-
},
|
| 2065 |
-
"Probability": {
|
| 2066 |
-
"Average Score": 0.0,
|
| 2067 |
-
"Standard Deviation": 0.0,
|
| 2068 |
-
"Rank": 54
|
| 2069 |
-
},
|
| 2070 |
-
"Logical": {
|
| 2071 |
-
"Average Score": 0.0,
|
| 2072 |
-
"Standard Deviation": 0.0,
|
| 2073 |
-
"Rank": 53
|
| 2074 |
-
},
|
| 2075 |
-
"Social": {
|
| 2076 |
-
"Average Score": 0.030792528,
|
| 2077 |
-
"Standard Deviation": 0.007518796391,
|
| 2078 |
-
"Rank": 53
|
| 2079 |
-
}
|
| 2080 |
-
}
|
| 2081 |
-
}
|
| 2082 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/models_2024-10-09-05:17:38.810960.json
DELETED
|
@@ -1,2327 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"config": {
|
| 4 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 5 |
-
"organization": "OpenAI",
|
| 6 |
-
"license": "Proprietary",
|
| 7 |
-
"knowledge_cutoff": "2023/10"
|
| 8 |
-
},
|
| 9 |
-
"results": {
|
| 10 |
-
"OVERALL": {
|
| 11 |
-
"Average Score": 0.974329609,
|
| 12 |
-
"Standard Deviation": 0.005024959031,
|
| 13 |
-
"Rank": 2
|
| 14 |
-
},
|
| 15 |
-
"Geometry": {
|
| 16 |
-
"Average Score": 0.976028578,
|
| 17 |
-
"Standard Deviation": 0.01507912373,
|
| 18 |
-
"Rank": 3
|
| 19 |
-
},
|
| 20 |
-
"Algebra": {
|
| 21 |
-
"Average Score": 0.951199453,
|
| 22 |
-
"Standard Deviation": 0.08452452108,
|
| 23 |
-
"Rank": 3
|
| 24 |
-
},
|
| 25 |
-
"Probability": {
|
| 26 |
-
"Average Score": 0.842116641,
|
| 27 |
-
"Standard Deviation": 0.006267759054,
|
| 28 |
-
"Rank": 3
|
| 29 |
-
},
|
| 30 |
-
"Logical": {
|
| 31 |
-
"Average Score": 0.828490728,
|
| 32 |
-
"Standard Deviation": 0.009134213144,
|
| 33 |
-
"Rank": 3
|
| 34 |
-
},
|
| 35 |
-
"Social": {
|
| 36 |
-
"Average Score": 0.815902987,
|
| 37 |
-
"Standard Deviation": 0.0196254222,
|
| 38 |
-
"Rank": 4
|
| 39 |
-
},
|
| 40 |
-
"Chemistry": {
|
| 41 |
-
"Average Score": 100.0,
|
| 42 |
-
"Standard Deviation": null,
|
| 43 |
-
"Rank": 1
|
| 44 |
-
}
|
| 45 |
-
}
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"config": {
|
| 49 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 50 |
-
"organization": "OpenAI",
|
| 51 |
-
"license": "Proprietary",
|
| 52 |
-
"knowledge_cutoff": "2023/10"
|
| 53 |
-
},
|
| 54 |
-
"results": {
|
| 55 |
-
"OVERALL": {
|
| 56 |
-
"Average Score": 0.846571548,
|
| 57 |
-
"Standard Deviation": 0.03394056554,
|
| 58 |
-
"Rank": 6
|
| 59 |
-
},
|
| 60 |
-
"Geometry": {
|
| 61 |
-
"Average Score": 0.99773096,
|
| 62 |
-
"Standard Deviation": 0.002835555172,
|
| 63 |
-
"Rank": 1
|
| 64 |
-
},
|
| 65 |
-
"Algebra": {
|
| 66 |
-
"Average Score": 1.0,
|
| 67 |
-
"Standard Deviation": 0.0,
|
| 68 |
-
"Rank": 1
|
| 69 |
-
},
|
| 70 |
-
"Probability": {
|
| 71 |
-
"Average Score": 0.78855795,
|
| 72 |
-
"Standard Deviation": 0.008188675452,
|
| 73 |
-
"Rank": 6
|
| 74 |
-
},
|
| 75 |
-
"Logical": {
|
| 76 |
-
"Average Score": 0.668635768,
|
| 77 |
-
"Standard Deviation": 0.03466314094,
|
| 78 |
-
"Rank": 11
|
| 79 |
-
},
|
| 80 |
-
"Social": {
|
| 81 |
-
"Average Score": 0.680417314,
|
| 82 |
-
"Standard Deviation": 0.00656867063,
|
| 83 |
-
"Rank": 9
|
| 84 |
-
},
|
| 85 |
-
"Chemistry": {
|
| 86 |
-
"Average Score": 92.43090226400756,
|
| 87 |
-
"Standard Deviation": null,
|
| 88 |
-
"Rank": 2
|
| 89 |
-
}
|
| 90 |
-
}
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"config": {
|
| 94 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 95 |
-
"organization": "OpenAI",
|
| 96 |
-
"license": "Proprietary",
|
| 97 |
-
"knowledge_cutoff": "2023/10"
|
| 98 |
-
},
|
| 99 |
-
"results": {
|
| 100 |
-
"OVERALL": {
|
| 101 |
-
"Average Score": 0.846334477,
|
| 102 |
-
"Standard Deviation": 0.09377911572,
|
| 103 |
-
"Rank": 7
|
| 104 |
-
},
|
| 105 |
-
"Geometry": {
|
| 106 |
-
"Average Score": 0.972472377,
|
| 107 |
-
"Standard Deviation": 0.01648274205,
|
| 108 |
-
"Rank": 4
|
| 109 |
-
},
|
| 110 |
-
"Algebra": {
|
| 111 |
-
"Average Score": 0.995511298,
|
| 112 |
-
"Standard Deviation": 0.004097802515,
|
| 113 |
-
"Rank": 2
|
| 114 |
-
},
|
| 115 |
-
"Probability": {
|
| 116 |
-
"Average Score": 0.812149974,
|
| 117 |
-
"Standard Deviation": 0.007669585485,
|
| 118 |
-
"Rank": 4
|
| 119 |
-
},
|
| 120 |
-
"Logical": {
|
| 121 |
-
"Average Score": 0.755019692,
|
| 122 |
-
"Standard Deviation": 0.008149588572,
|
| 123 |
-
"Rank": 6
|
| 124 |
-
},
|
| 125 |
-
"Social": {
|
| 126 |
-
"Average Score": 0.609875087,
|
| 127 |
-
"Standard Deviation": 0.038729239,
|
| 128 |
-
"Rank": 14
|
| 129 |
-
},
|
| 130 |
-
"Chemistry": {
|
| 131 |
-
"Average Score": 79.1592634699295,
|
| 132 |
-
"Standard Deviation": null,
|
| 133 |
-
"Rank": 7
|
| 134 |
-
}
|
| 135 |
-
}
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"config": {
|
| 139 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 140 |
-
"organization": "OpenAI",
|
| 141 |
-
"license": "Proprietary",
|
| 142 |
-
"knowledge_cutoff": "2023/12"
|
| 143 |
-
},
|
| 144 |
-
"results": {
|
| 145 |
-
"OVERALL": {
|
| 146 |
-
"Average Score": 0.855357972,
|
| 147 |
-
"Standard Deviation": 0.1016986368,
|
| 148 |
-
"Rank": 4
|
| 149 |
-
},
|
| 150 |
-
"Geometry": {
|
| 151 |
-
"Average Score": 0.95374588,
|
| 152 |
-
"Standard Deviation": 0.03109307166,
|
| 153 |
-
"Rank": 5
|
| 154 |
-
},
|
| 155 |
-
"Algebra": {
|
| 156 |
-
"Average Score": 0.930945223,
|
| 157 |
-
"Standard Deviation": 0.06705136813,
|
| 158 |
-
"Rank": 4
|
| 159 |
-
},
|
| 160 |
-
"Probability": {
|
| 161 |
-
"Average Score": 0.750705448,
|
| 162 |
-
"Standard Deviation": 0.05944483103,
|
| 163 |
-
"Rank": 8
|
| 164 |
-
},
|
| 165 |
-
"Logical": {
|
| 166 |
-
"Average Score": 0.77906699,
|
| 167 |
-
"Standard Deviation": 0.007406734161,
|
| 168 |
-
"Rank": 4
|
| 169 |
-
},
|
| 170 |
-
"Social": {
|
| 171 |
-
"Average Score": 0.715935163,
|
| 172 |
-
"Standard Deviation": 0.1209141409,
|
| 173 |
-
"Rank": 7
|
| 174 |
-
},
|
| 175 |
-
"Chemistry": {
|
| 176 |
-
"Average Score": 70.73143363230263,
|
| 177 |
-
"Standard Deviation": null,
|
| 178 |
-
"Rank": 12
|
| 179 |
-
}
|
| 180 |
-
}
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"config": {
|
| 184 |
-
"model_name": "gemini-1.5-pro-001",
|
| 185 |
-
"organization": "Google",
|
| 186 |
-
"license": "Proprietary",
|
| 187 |
-
"knowledge_cutoff": "2023/11"
|
| 188 |
-
},
|
| 189 |
-
"results": {
|
| 190 |
-
"OVERALL": {
|
| 191 |
-
"Average Score": 0.797187842,
|
| 192 |
-
"Standard Deviation": 0.0272375249,
|
| 193 |
-
"Rank": 10
|
| 194 |
-
},
|
| 195 |
-
"Geometry": {
|
| 196 |
-
"Average Score": 0.9947169,
|
| 197 |
-
"Standard Deviation": 0.009150597621,
|
| 198 |
-
"Rank": 2
|
| 199 |
-
},
|
| 200 |
-
"Algebra": {
|
| 201 |
-
"Average Score": 0.857464301,
|
| 202 |
-
"Standard Deviation": 0.05014285338,
|
| 203 |
-
"Rank": 5
|
| 204 |
-
},
|
| 205 |
-
"Probability": {
|
| 206 |
-
"Average Score": 0.651781767,
|
| 207 |
-
"Standard Deviation": 0.04156998547,
|
| 208 |
-
"Rank": 12
|
| 209 |
-
},
|
| 210 |
-
"Logical": {
|
| 211 |
-
"Average Score": 0.739745471,
|
| 212 |
-
"Standard Deviation": 0.01631532019,
|
| 213 |
-
"Rank": 7
|
| 214 |
-
},
|
| 215 |
-
"Social": {
|
| 216 |
-
"Average Score": 0.649601885,
|
| 217 |
-
"Standard Deviation": 0.104854889,
|
| 218 |
-
"Rank": 12
|
| 219 |
-
}
|
| 220 |
-
}
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"config": {
|
| 224 |
-
"model_name": "qwen2-72b-instruct",
|
| 225 |
-
"organization": "Alibaba",
|
| 226 |
-
"license": "Qianwen LICENSE",
|
| 227 |
-
"knowledge_cutoff": "2024/09"
|
| 228 |
-
},
|
| 229 |
-
"results": {
|
| 230 |
-
"OVERALL": {
|
| 231 |
-
"Average Score": 0.737918558,
|
| 232 |
-
"Standard Deviation": 0.09069077339,
|
| 233 |
-
"Rank": 11
|
| 234 |
-
},
|
| 235 |
-
"Geometry": {
|
| 236 |
-
"Average Score": 0.796870305,
|
| 237 |
-
"Standard Deviation": 0.0509025346,
|
| 238 |
-
"Rank": 9
|
| 239 |
-
},
|
| 240 |
-
"Algebra": {
|
| 241 |
-
"Average Score": 0.836194231,
|
| 242 |
-
"Standard Deviation": 0.04517093028,
|
| 243 |
-
"Rank": 6
|
| 244 |
-
},
|
| 245 |
-
"Probability": {
|
| 246 |
-
"Average Score": 0.788068004,
|
| 247 |
-
"Standard Deviation": 0.007288989044,
|
| 248 |
-
"Rank": 7
|
| 249 |
-
},
|
| 250 |
-
"Logical": {
|
| 251 |
-
"Average Score": 0.619300904,
|
| 252 |
-
"Standard Deviation": 0.06377931612,
|
| 253 |
-
"Rank": 15
|
| 254 |
-
},
|
| 255 |
-
"Social": {
|
| 256 |
-
"Average Score": 0.652578786,
|
| 257 |
-
"Standard Deviation": 0.04259293171,
|
| 258 |
-
"Rank": 11
|
| 259 |
-
},
|
| 260 |
-
"Chemistry": {
|
| 261 |
-
"Average Score": 73.54037778797029,
|
| 262 |
-
"Standard Deviation": null,
|
| 263 |
-
"Rank": 8
|
| 264 |
-
}
|
| 265 |
-
}
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"config": {
|
| 269 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 270 |
-
"organization": "OpenAI",
|
| 271 |
-
"license": "Proprietary",
|
| 272 |
-
"knowledge_cutoff": "2023/10"
|
| 273 |
-
},
|
| 274 |
-
"results": {
|
| 275 |
-
"OVERALL": {
|
| 276 |
-
"Average Score": 0.847694133,
|
| 277 |
-
"Standard Deviation": 0.02164304402,
|
| 278 |
-
"Rank": 5
|
| 279 |
-
},
|
| 280 |
-
"Geometry": {
|
| 281 |
-
"Average Score": 0.946650435,
|
| 282 |
-
"Standard Deviation": 0.01831236482,
|
| 283 |
-
"Rank": 7
|
| 284 |
-
},
|
| 285 |
-
"Algebra": {
|
| 286 |
-
"Average Score": 0.796243022,
|
| 287 |
-
"Standard Deviation": 0.05537539202,
|
| 288 |
-
"Rank": 7
|
| 289 |
-
},
|
| 290 |
-
"Probability": {
|
| 291 |
-
"Average Score": 0.798402685,
|
| 292 |
-
"Standard Deviation": 0.009404491967,
|
| 293 |
-
"Rank": 5
|
| 294 |
-
},
|
| 295 |
-
"Logical": {
|
| 296 |
-
"Average Score": 0.727009735,
|
| 297 |
-
"Standard Deviation": 0.02628110141,
|
| 298 |
-
"Rank": 8
|
| 299 |
-
},
|
| 300 |
-
"Social": {
|
| 301 |
-
"Average Score": 0.691949855,
|
| 302 |
-
"Standard Deviation": 0.02072934333,
|
| 303 |
-
"Rank": 8
|
| 304 |
-
},
|
| 305 |
-
"Chemistry": {
|
| 306 |
-
"Average Score": 88.3877070580296,
|
| 307 |
-
"Standard Deviation": null,
|
| 308 |
-
"Rank": 3
|
| 309 |
-
}
|
| 310 |
-
}
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"config": {
|
| 314 |
-
"model_name": "claude-3.5-sonnet",
|
| 315 |
-
"organization": "Anthropic",
|
| 316 |
-
"license": "Proprietary",
|
| 317 |
-
"knowledge_cutoff": "2024/04"
|
| 318 |
-
},
|
| 319 |
-
"results": {
|
| 320 |
-
"OVERALL": {
|
| 321 |
-
"Average Score": 0.839004422,
|
| 322 |
-
"Standard Deviation": 0.1461079564,
|
| 323 |
-
"Rank": 8
|
| 324 |
-
},
|
| 325 |
-
"Geometry": {
|
| 326 |
-
"Average Score": 0.95316419,
|
| 327 |
-
"Standard Deviation": 0.02081192856,
|
| 328 |
-
"Rank": 6
|
| 329 |
-
},
|
| 330 |
-
"Algebra": {
|
| 331 |
-
"Average Score": 0.759789952,
|
| 332 |
-
"Standard Deviation": 0.02611765096,
|
| 333 |
-
"Rank": 8
|
| 334 |
-
},
|
| 335 |
-
"Probability": {
|
| 336 |
-
"Average Score": 0.707730127,
|
| 337 |
-
"Standard Deviation": 0.0394436664,
|
| 338 |
-
"Rank": 10
|
| 339 |
-
},
|
| 340 |
-
"Logical": {
|
| 341 |
-
"Average Score": 0.77342666,
|
| 342 |
-
"Standard Deviation": 0.002892426458,
|
| 343 |
-
"Rank": 5
|
| 344 |
-
},
|
| 345 |
-
"Social": {
|
| 346 |
-
"Average Score": 0.790002247,
|
| 347 |
-
"Standard Deviation": 0.1007410022,
|
| 348 |
-
"Rank": 5
|
| 349 |
-
},
|
| 350 |
-
"Chemistry": {
|
| 351 |
-
"Average Score": 82.37734076815008,
|
| 352 |
-
"Standard Deviation": null,
|
| 353 |
-
"Rank": 6
|
| 354 |
-
}
|
| 355 |
-
}
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"config": {
|
| 359 |
-
"model_name": "o1-mini",
|
| 360 |
-
"organization": "OpenAI",
|
| 361 |
-
"license": "Proprietary",
|
| 362 |
-
"knowledge_cutoff": "2023/10"
|
| 363 |
-
},
|
| 364 |
-
"results": {
|
| 365 |
-
"OVERALL": {
|
| 366 |
-
"Average Score": 1.0,
|
| 367 |
-
"Standard Deviation": 0.0,
|
| 368 |
-
"Rank": 1
|
| 369 |
-
},
|
| 370 |
-
"Geometry": {
|
| 371 |
-
"Average Score": "N/A",
|
| 372 |
-
"Standard Deviation": "N/A",
|
| 373 |
-
"Rank": "N/A"
|
| 374 |
-
},
|
| 375 |
-
"Algebra": {
|
| 376 |
-
"Average Score": "N/A",
|
| 377 |
-
"Standard Deviation": "N/A",
|
| 378 |
-
"Rank": "N/A"
|
| 379 |
-
},
|
| 380 |
-
"Probability": {
|
| 381 |
-
"Average Score": 1.0,
|
| 382 |
-
"Standard Deviation": 0.0,
|
| 383 |
-
"Rank": 1
|
| 384 |
-
},
|
| 385 |
-
"Logical": {
|
| 386 |
-
"Average Score": 1.0,
|
| 387 |
-
"Standard Deviation": 0.0,
|
| 388 |
-
"Rank": 1
|
| 389 |
-
},
|
| 390 |
-
"Social": {
|
| 391 |
-
"Average Score": 0.993974241,
|
| 392 |
-
"Standard Deviation": 0.001996882328,
|
| 393 |
-
"Rank": 2
|
| 394 |
-
}
|
| 395 |
-
}
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"config": {
|
| 399 |
-
"model_name": "o1-preview",
|
| 400 |
-
"organization": "OpenAI",
|
| 401 |
-
"license": "Proprietary",
|
| 402 |
-
"knowledge_cutoff": "2023/10"
|
| 403 |
-
},
|
| 404 |
-
"results": {
|
| 405 |
-
"OVERALL": {
|
| 406 |
-
"Average Score": 0.945884589,
|
| 407 |
-
"Standard Deviation": 0.01059250762,
|
| 408 |
-
"Rank": 3
|
| 409 |
-
},
|
| 410 |
-
"Geometry": {
|
| 411 |
-
"Average Score": "N/A",
|
| 412 |
-
"Standard Deviation": "N/A",
|
| 413 |
-
"Rank": "N/A"
|
| 414 |
-
},
|
| 415 |
-
"Algebra": {
|
| 416 |
-
"Average Score": "N/A",
|
| 417 |
-
"Standard Deviation": "N/A",
|
| 418 |
-
"Rank": "N/A"
|
| 419 |
-
},
|
| 420 |
-
"Probability": {
|
| 421 |
-
"Average Score": 0.964666392,
|
| 422 |
-
"Standard Deviation": 0.003139983398,
|
| 423 |
-
"Rank": 2
|
| 424 |
-
},
|
| 425 |
-
"Logical": {
|
| 426 |
-
"Average Score": 0.987950057,
|
| 427 |
-
"Standard Deviation": 0.004881220327,
|
| 428 |
-
"Rank": 2
|
| 429 |
-
},
|
| 430 |
-
"Social": {
|
| 431 |
-
"Average Score": 1.0,
|
| 432 |
-
"Standard Deviation": 0.0,
|
| 433 |
-
"Rank": 1
|
| 434 |
-
}
|
| 435 |
-
}
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"config": {
|
| 439 |
-
"model_name": "gemini-1.5-flash-001",
|
| 440 |
-
"organization": "Google",
|
| 441 |
-
"license": "Proprietary",
|
| 442 |
-
"knowledge_cutoff": "2023/11"
|
| 443 |
-
},
|
| 444 |
-
"results": {
|
| 445 |
-
"OVERALL": {
|
| 446 |
-
"Average Score": 0.726493401,
|
| 447 |
-
"Standard Deviation": 0.01113913725,
|
| 448 |
-
"Rank": 12
|
| 449 |
-
},
|
| 450 |
-
"Geometry": {
|
| 451 |
-
"Average Score": 0.804144103,
|
| 452 |
-
"Standard Deviation": 0.1327142178,
|
| 453 |
-
"Rank": 8
|
| 454 |
-
},
|
| 455 |
-
"Algebra": {
|
| 456 |
-
"Average Score": 0.731776765,
|
| 457 |
-
"Standard Deviation": 0.02594657111,
|
| 458 |
-
"Rank": 11
|
| 459 |
-
},
|
| 460 |
-
"Probability": {
|
| 461 |
-
"Average Score": 0.614461891,
|
| 462 |
-
"Standard Deviation": 0.04690131826,
|
| 463 |
-
"Rank": 15
|
| 464 |
-
},
|
| 465 |
-
"Logical": {
|
| 466 |
-
"Average Score": 0.630805991,
|
| 467 |
-
"Standard Deviation": 0.04871350612,
|
| 468 |
-
"Rank": 13
|
| 469 |
-
},
|
| 470 |
-
"Social": {
|
| 471 |
-
"Average Score": 0.555933822,
|
| 472 |
-
"Standard Deviation": 0.1029934524,
|
| 473 |
-
"Rank": 16
|
| 474 |
-
},
|
| 475 |
-
"Chemistry": {
|
| 476 |
-
"Average Score": 72.1127762005651,
|
| 477 |
-
"Standard Deviation": null,
|
| 478 |
-
"Rank": 11
|
| 479 |
-
}
|
| 480 |
-
}
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"config": {
|
| 484 |
-
"model_name": "gpt4-1106",
|
| 485 |
-
"organization": "OpenAI",
|
| 486 |
-
"license": "Proprietary",
|
| 487 |
-
"knowledge_cutoff": "2024/04"
|
| 488 |
-
},
|
| 489 |
-
"results": {
|
| 490 |
-
"OVERALL": {
|
| 491 |
-
"Average Score": 0.816347784,
|
| 492 |
-
"Standard Deviation": 0.1566815755,
|
| 493 |
-
"Rank": 9
|
| 494 |
-
},
|
| 495 |
-
"Geometry": {
|
| 496 |
-
"Average Score": 0.71843088,
|
| 497 |
-
"Standard Deviation": 0.04778038294,
|
| 498 |
-
"Rank": 13
|
| 499 |
-
},
|
| 500 |
-
"Algebra": {
|
| 501 |
-
"Average Score": 0.712910417,
|
| 502 |
-
"Standard Deviation": 0.02581828898,
|
| 503 |
-
"Rank": 12
|
| 504 |
-
},
|
| 505 |
-
"Probability": {
|
| 506 |
-
"Average Score": 0.623947619,
|
| 507 |
-
"Standard Deviation": 0.03502982933,
|
| 508 |
-
"Rank": 14
|
| 509 |
-
},
|
| 510 |
-
"Logical": {
|
| 511 |
-
"Average Score": 0.637482274,
|
| 512 |
-
"Standard Deviation": 0.04158809888,
|
| 513 |
-
"Rank": 12
|
| 514 |
-
},
|
| 515 |
-
"Social": {
|
| 516 |
-
"Average Score": 0.450609816,
|
| 517 |
-
"Standard Deviation": 0.05208655446,
|
| 518 |
-
"Rank": 23
|
| 519 |
-
},
|
| 520 |
-
"Chemistry": {
|
| 521 |
-
"Average Score": 69.11824072252848,
|
| 522 |
-
"Standard Deviation": null,
|
| 523 |
-
"Rank": 13
|
| 524 |
-
}
|
| 525 |
-
}
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"config": {
|
| 529 |
-
"model_name": "gemma-2-27b-it",
|
| 530 |
-
"organization": "Google",
|
| 531 |
-
"license": "Gemma License",
|
| 532 |
-
"knowledge_cutoff": "2024/06"
|
| 533 |
-
},
|
| 534 |
-
"results": {
|
| 535 |
-
"OVERALL": {
|
| 536 |
-
"Average Score": 0.624169623,
|
| 537 |
-
"Standard Deviation": 0.1048365121,
|
| 538 |
-
"Rank": 15
|
| 539 |
-
},
|
| 540 |
-
"Geometry": {
|
| 541 |
-
"Average Score": 0.60112744,
|
| 542 |
-
"Standard Deviation": 0.0469109952,
|
| 543 |
-
"Rank": 19
|
| 544 |
-
},
|
| 545 |
-
"Algebra": {
|
| 546 |
-
"Average Score": 0.687955914,
|
| 547 |
-
"Standard Deviation": 0.01959958192,
|
| 548 |
-
"Rank": 13
|
| 549 |
-
},
|
| 550 |
-
"Probability": {
|
| 551 |
-
"Average Score": 0.589524771,
|
| 552 |
-
"Standard Deviation": 0.03112689325,
|
| 553 |
-
"Rank": 16
|
| 554 |
-
},
|
| 555 |
-
"Logical": {
|
| 556 |
-
"Average Score": 0.614978944,
|
| 557 |
-
"Standard Deviation": 0.05710657859,
|
| 558 |
-
"Rank": 16
|
| 559 |
-
},
|
| 560 |
-
"Social": {
|
| 561 |
-
"Average Score": 0.487844257,
|
| 562 |
-
"Standard Deviation": 0.05857760809,
|
| 563 |
-
"Rank": 20
|
| 564 |
-
},
|
| 565 |
-
"Chemistry": {
|
| 566 |
-
"Average Score": 63.28920072143611,
|
| 567 |
-
"Standard Deviation": null,
|
| 568 |
-
"Rank": 15
|
| 569 |
-
}
|
| 570 |
-
}
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"config": {
|
| 574 |
-
"model_name": "claude-3-opus",
|
| 575 |
-
"organization": "Anthropic",
|
| 576 |
-
"license": "Proprietary",
|
| 577 |
-
"knowledge_cutoff": "2023/08"
|
| 578 |
-
},
|
| 579 |
-
"results": {
|
| 580 |
-
"OVERALL": {
|
| 581 |
-
"Average Score": 0.650636271,
|
| 582 |
-
"Standard Deviation": 0.1197773541,
|
| 583 |
-
"Rank": 14
|
| 584 |
-
},
|
| 585 |
-
"Geometry": {
|
| 586 |
-
"Average Score": 0.7215743,
|
| 587 |
-
"Standard Deviation": 0.04712598358,
|
| 588 |
-
"Rank": 12
|
| 589 |
-
},
|
| 590 |
-
"Algebra": {
|
| 591 |
-
"Average Score": 0.68777327,
|
| 592 |
-
"Standard Deviation": 0.02382683713,
|
| 593 |
-
"Rank": 14
|
| 594 |
-
},
|
| 595 |
-
"Probability": {
|
| 596 |
-
"Average Score": 0.626471421,
|
| 597 |
-
"Standard Deviation": 0.02911817976,
|
| 598 |
-
"Rank": 13
|
| 599 |
-
},
|
| 600 |
-
"Logical": {
|
| 601 |
-
"Average Score": 0.692346381,
|
| 602 |
-
"Standard Deviation": 0.03617185198,
|
| 603 |
-
"Rank": 10
|
| 604 |
-
},
|
| 605 |
-
"Social": {
|
| 606 |
-
"Average Score": 0.663410854,
|
| 607 |
-
"Standard Deviation": 0.09540220876,
|
| 608 |
-
"Rank": 10
|
| 609 |
-
},
|
| 610 |
-
"Chemistry": {
|
| 611 |
-
"Average Score": 73.5404403567132,
|
| 612 |
-
"Standard Deviation": null,
|
| 613 |
-
"Rank": 9
|
| 614 |
-
}
|
| 615 |
-
}
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"config": {
|
| 619 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 620 |
-
"organization": "Google",
|
| 621 |
-
"license": "Gemma License",
|
| 622 |
-
"knowledge_cutoff": "2024/07"
|
| 623 |
-
},
|
| 624 |
-
"results": {
|
| 625 |
-
"OVERALL": {
|
| 626 |
-
"Average Score": "N/A",
|
| 627 |
-
"Standard Deviation": "N/A",
|
| 628 |
-
"Rank": "N/A"
|
| 629 |
-
},
|
| 630 |
-
"Geometry": {
|
| 631 |
-
"Average Score": 0.582787508,
|
| 632 |
-
"Standard Deviation": 0.03965204074,
|
| 633 |
-
"Rank": 20
|
| 634 |
-
},
|
| 635 |
-
"Algebra": {
|
| 636 |
-
"Average Score": 0.658648133,
|
| 637 |
-
"Standard Deviation": 0.02565919856,
|
| 638 |
-
"Rank": 15
|
| 639 |
-
},
|
| 640 |
-
"Probability": {
|
| 641 |
-
"Average Score": 0.547861265,
|
| 642 |
-
"Standard Deviation": 0.02885209131,
|
| 643 |
-
"Rank": 19
|
| 644 |
-
},
|
| 645 |
-
"Logical": {
|
| 646 |
-
"Average Score": 0.540720893,
|
| 647 |
-
"Standard Deviation": 0.01970134508,
|
| 648 |
-
"Rank": 20
|
| 649 |
-
},
|
| 650 |
-
"Social": {
|
| 651 |
-
"Average Score": 0.635266187,
|
| 652 |
-
"Standard Deviation": 0.03620021751,
|
| 653 |
-
"Rank": 13
|
| 654 |
-
},
|
| 655 |
-
"Chemistry": {
|
| 656 |
-
"Average Score": 73.43757596214863,
|
| 657 |
-
"Standard Deviation": null,
|
| 658 |
-
"Rank": 10
|
| 659 |
-
}
|
| 660 |
-
}
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"config": {
|
| 664 |
-
"model_name": "qwen1.5-72b-chat",
|
| 665 |
-
"organization": "Alibaba",
|
| 666 |
-
"license": "Qianwen LICENSE",
|
| 667 |
-
"knowledge_cutoff": "2024/03"
|
| 668 |
-
},
|
| 669 |
-
"results": {
|
| 670 |
-
"OVERALL": {
|
| 671 |
-
"Average Score": 0.519549796,
|
| 672 |
-
"Standard Deviation": 0.00903634343,
|
| 673 |
-
"Rank": 18
|
| 674 |
-
},
|
| 675 |
-
"Geometry": {
|
| 676 |
-
"Average Score": 0.543139301,
|
| 677 |
-
"Standard Deviation": 0.03425202326,
|
| 678 |
-
"Rank": 24
|
| 679 |
-
},
|
| 680 |
-
"Algebra": {
|
| 681 |
-
"Average Score": 0.635228729,
|
| 682 |
-
"Standard Deviation": 0.01944043425,
|
| 683 |
-
"Rank": 16
|
| 684 |
-
},
|
| 685 |
-
"Probability": {
|
| 686 |
-
"Average Score": 0.486948658,
|
| 687 |
-
"Standard Deviation": 0.06064655315,
|
| 688 |
-
"Rank": 23
|
| 689 |
-
},
|
| 690 |
-
"Logical": {
|
| 691 |
-
"Average Score": 0.284069394,
|
| 692 |
-
"Standard Deviation": 0.02686608506,
|
| 693 |
-
"Rank": 33
|
| 694 |
-
},
|
| 695 |
-
"Social": {
|
| 696 |
-
"Average Score": 0.415007627,
|
| 697 |
-
"Standard Deviation": 0.03920053159,
|
| 698 |
-
"Rank": 24
|
| 699 |
-
},
|
| 700 |
-
"Chemistry": {
|
| 701 |
-
"Average Score": 48.69302376665551,
|
| 702 |
-
"Standard Deviation": null,
|
| 703 |
-
"Rank": 21
|
| 704 |
-
}
|
| 705 |
-
}
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"config": {
|
| 709 |
-
"model_name": "qwen1.5-32b-chat",
|
| 710 |
-
"organization": "Alibaba",
|
| 711 |
-
"license": "Qianwen LICENSE",
|
| 712 |
-
"knowledge_cutoff": "2024/03"
|
| 713 |
-
},
|
| 714 |
-
"results": {
|
| 715 |
-
"OVERALL": {
|
| 716 |
-
"Average Score": 0.393789407,
|
| 717 |
-
"Standard Deviation": 0.05413770095,
|
| 718 |
-
"Rank": 29
|
| 719 |
-
},
|
| 720 |
-
"Geometry": {
|
| 721 |
-
"Average Score": 0.51086835,
|
| 722 |
-
"Standard Deviation": 0.04052471998,
|
| 723 |
-
"Rank": 27
|
| 724 |
-
},
|
| 725 |
-
"Algebra": {
|
| 726 |
-
"Average Score": 0.609003168,
|
| 727 |
-
"Standard Deviation": 0.04874143541,
|
| 728 |
-
"Rank": 17
|
| 729 |
-
},
|
| 730 |
-
"Probability": {
|
| 731 |
-
"Average Score": 0.476300002,
|
| 732 |
-
"Standard Deviation": 0.05322403912,
|
| 733 |
-
"Rank": 24
|
| 734 |
-
},
|
| 735 |
-
"Logical": {
|
| 736 |
-
"Average Score": 0.331781014,
|
| 737 |
-
"Standard Deviation": 0.004938997686,
|
| 738 |
-
"Rank": 30
|
| 739 |
-
},
|
| 740 |
-
"Social": {
|
| 741 |
-
"Average Score": 0.380987334,
|
| 742 |
-
"Standard Deviation": 0.03762251776,
|
| 743 |
-
"Rank": 26
|
| 744 |
-
},
|
| 745 |
-
"Chemistry": {
|
| 746 |
-
"Average Score": 45.14284028264288,
|
| 747 |
-
"Standard Deviation": null,
|
| 748 |
-
"Rank": 25
|
| 749 |
-
}
|
| 750 |
-
}
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"config": {
|
| 754 |
-
"model_name": "google-gemma-2-9b-it",
|
| 755 |
-
"organization": "Google",
|
| 756 |
-
"license": "Proprietary",
|
| 757 |
-
"knowledge_cutoff": "2024/06"
|
| 758 |
-
},
|
| 759 |
-
"results": {
|
| 760 |
-
"OVERALL": {
|
| 761 |
-
"Average Score": 0.489663449,
|
| 762 |
-
"Standard Deviation": 0.002595702019,
|
| 763 |
-
"Rank": 21
|
| 764 |
-
},
|
| 765 |
-
"Geometry": {
|
| 766 |
-
"Average Score": 0.575371308,
|
| 767 |
-
"Standard Deviation": 0.03556220251,
|
| 768 |
-
"Rank": 22
|
| 769 |
-
},
|
| 770 |
-
"Algebra": {
|
| 771 |
-
"Average Score": 0.597045661,
|
| 772 |
-
"Standard Deviation": 0.0313828123,
|
| 773 |
-
"Rank": 18
|
| 774 |
-
},
|
| 775 |
-
"Probability": {
|
| 776 |
-
"Average Score": 0.589221807,
|
| 777 |
-
"Standard Deviation": 0.03110811656,
|
| 778 |
-
"Rank": 18
|
| 779 |
-
},
|
| 780 |
-
"Logical": {
|
| 781 |
-
"Average Score": 0.587579897,
|
| 782 |
-
"Standard Deviation": 0.05512716783,
|
| 783 |
-
"Rank": 18
|
| 784 |
-
},
|
| 785 |
-
"Social": {
|
| 786 |
-
"Average Score": 0.768337958,
|
| 787 |
-
"Standard Deviation": 0.04078610476,
|
| 788 |
-
"Rank": 6
|
| 789 |
-
},
|
| 790 |
-
"Chemistry": {
|
| 791 |
-
"Average Score": 54.03167523687635,
|
| 792 |
-
"Standard Deviation": null,
|
| 793 |
-
"Rank": 18
|
| 794 |
-
}
|
| 795 |
-
}
|
| 796 |
-
},
|
| 797 |
-
{
|
| 798 |
-
"config": {
|
| 799 |
-
"model_name": "yi-1.5-34b-chat",
|
| 800 |
-
"organization": "01 AI",
|
| 801 |
-
"license": "Proprietary",
|
| 802 |
-
"knowledge_cutoff": "2024/05"
|
| 803 |
-
},
|
| 804 |
-
"results": {
|
| 805 |
-
"OVERALL": {
|
| 806 |
-
"Average Score": 0.607812897,
|
| 807 |
-
"Standard Deviation": 0.1440881293,
|
| 808 |
-
"Rank": 16
|
| 809 |
-
},
|
| 810 |
-
"Geometry": {
|
| 811 |
-
"Average Score": 0.566666724,
|
| 812 |
-
"Standard Deviation": 0.04001381658,
|
| 813 |
-
"Rank": 23
|
| 814 |
-
},
|
| 815 |
-
"Algebra": {
|
| 816 |
-
"Average Score": 0.590997292,
|
| 817 |
-
"Standard Deviation": 0.03594087315,
|
| 818 |
-
"Rank": 19
|
| 819 |
-
},
|
| 820 |
-
"Probability": {
|
| 821 |
-
"Average Score": 0.589524589,
|
| 822 |
-
"Standard Deviation": 0.03112618772,
|
| 823 |
-
"Rank": 17
|
| 824 |
-
},
|
| 825 |
-
"Logical": {
|
| 826 |
-
"Average Score": 0.574105508,
|
| 827 |
-
"Standard Deviation": 0.03441737941,
|
| 828 |
-
"Rank": 19
|
| 829 |
-
},
|
| 830 |
-
"Social": {
|
| 831 |
-
"Average Score": 0.516980832,
|
| 832 |
-
"Standard Deviation": 0.03369347985,
|
| 833 |
-
"Rank": 19
|
| 834 |
-
},
|
| 835 |
-
"Chemistry": {
|
| 836 |
-
"Average Score": 52.148798061768964,
|
| 837 |
-
"Standard Deviation": null,
|
| 838 |
-
"Rank": 19
|
| 839 |
-
}
|
| 840 |
-
}
|
| 841 |
-
},
|
| 842 |
-
{
|
| 843 |
-
"config": {
|
| 844 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 845 |
-
"organization": "Meta",
|
| 846 |
-
"license": "Llama 3.1 Community",
|
| 847 |
-
"knowledge_cutoff": "2023/12"
|
| 848 |
-
},
|
| 849 |
-
"results": {
|
| 850 |
-
"OVERALL": {
|
| 851 |
-
"Average Score": 0.505936324,
|
| 852 |
-
"Standard Deviation": 0.05286756493,
|
| 853 |
-
"Rank": 19
|
| 854 |
-
},
|
| 855 |
-
"Geometry": {
|
| 856 |
-
"Average Score": 0.522442162,
|
| 857 |
-
"Standard Deviation": 0.03908236317,
|
| 858 |
-
"Rank": 25
|
| 859 |
-
},
|
| 860 |
-
"Algebra": {
|
| 861 |
-
"Average Score": 0.582702645,
|
| 862 |
-
"Standard Deviation": 0.05002277711,
|
| 863 |
-
"Rank": 20
|
| 864 |
-
},
|
| 865 |
-
"Probability": {
|
| 866 |
-
"Average Score": 0.495001149,
|
| 867 |
-
"Standard Deviation": 0.05244587037,
|
| 868 |
-
"Rank": 22
|
| 869 |
-
},
|
| 870 |
-
"Logical": {
|
| 871 |
-
"Average Score": 0.443030561,
|
| 872 |
-
"Standard Deviation": 0.01343820628,
|
| 873 |
-
"Rank": 25
|
| 874 |
-
},
|
| 875 |
-
"Social": {
|
| 876 |
-
"Average Score": 0.329195941,
|
| 877 |
-
"Standard Deviation": 0.03925019528,
|
| 878 |
-
"Rank": 30
|
| 879 |
-
},
|
| 880 |
-
"Chemistry": {
|
| 881 |
-
"Average Score": 44.41846841004584,
|
| 882 |
-
"Standard Deviation": null,
|
| 883 |
-
"Rank": 27
|
| 884 |
-
}
|
| 885 |
-
}
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"config": {
|
| 889 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 890 |
-
"organization": "OpenAI",
|
| 891 |
-
"license": "Proprietary",
|
| 892 |
-
"knowledge_cutoff": "2021/09"
|
| 893 |
-
},
|
| 894 |
-
"results": {
|
| 895 |
-
"OVERALL": {
|
| 896 |
-
"Average Score": 0.313398088,
|
| 897 |
-
"Standard Deviation": 0.09322528606,
|
| 898 |
-
"Rank": 40
|
| 899 |
-
},
|
| 900 |
-
"Geometry": {
|
| 901 |
-
"Average Score": 0.678714519,
|
| 902 |
-
"Standard Deviation": 0.05926546762,
|
| 903 |
-
"Rank": 14
|
| 904 |
-
},
|
| 905 |
-
"Algebra": {
|
| 906 |
-
"Average Score": 0.569296173,
|
| 907 |
-
"Standard Deviation": 0.05277281097,
|
| 908 |
-
"Rank": 21
|
| 909 |
-
},
|
| 910 |
-
"Probability": {
|
| 911 |
-
"Average Score": 0.448460767,
|
| 912 |
-
"Standard Deviation": 0.05768095196,
|
| 913 |
-
"Rank": 26
|
| 914 |
-
},
|
| 915 |
-
"Logical": {
|
| 916 |
-
"Average Score": 0.148521348,
|
| 917 |
-
"Standard Deviation": 0.04033712907,
|
| 918 |
-
"Rank": 45
|
| 919 |
-
},
|
| 920 |
-
"Social": {
|
| 921 |
-
"Average Score": 0.235071541,
|
| 922 |
-
"Standard Deviation": 0.02632892457,
|
| 923 |
-
"Rank": 39
|
| 924 |
-
},
|
| 925 |
-
"Chemistry": {
|
| 926 |
-
"Average Score": 40.46958736582551,
|
| 927 |
-
"Standard Deviation": null,
|
| 928 |
-
"Rank": 30
|
| 929 |
-
}
|
| 930 |
-
}
|
| 931 |
-
},
|
| 932 |
-
{
|
| 933 |
-
"config": {
|
| 934 |
-
"model_name": "llama-3-70b-instruct",
|
| 935 |
-
"organization": "Meta",
|
| 936 |
-
"license": "Llama 3 Community",
|
| 937 |
-
"knowledge_cutoff": "2023/12"
|
| 938 |
-
},
|
| 939 |
-
"results": {
|
| 940 |
-
"OVERALL": {
|
| 941 |
-
"Average Score": 0.456689885,
|
| 942 |
-
"Standard Deviation": 0.01385989995,
|
| 943 |
-
"Rank": 23
|
| 944 |
-
},
|
| 945 |
-
"Geometry": {
|
| 946 |
-
"Average Score": 0.516865529,
|
| 947 |
-
"Standard Deviation": 0.03858112564,
|
| 948 |
-
"Rank": 26
|
| 949 |
-
},
|
| 950 |
-
"Algebra": {
|
| 951 |
-
"Average Score": 0.566756531,
|
| 952 |
-
"Standard Deviation": 0.03369826926,
|
| 953 |
-
"Rank": 22
|
| 954 |
-
},
|
| 955 |
-
"Probability": {
|
| 956 |
-
"Average Score": 0.513857306,
|
| 957 |
-
"Standard Deviation": 0.05453699062,
|
| 958 |
-
"Rank": 21
|
| 959 |
-
},
|
| 960 |
-
"Logical": {
|
| 961 |
-
"Average Score": 0.713796415,
|
| 962 |
-
"Standard Deviation": 0.02031215107,
|
| 963 |
-
"Rank": 9
|
| 964 |
-
},
|
| 965 |
-
"Social": {
|
| 966 |
-
"Average Score": 0.45872939,
|
| 967 |
-
"Standard Deviation": 0.05347039576,
|
| 968 |
-
"Rank": 22
|
| 969 |
-
},
|
| 970 |
-
"Chemistry": {
|
| 971 |
-
"Average Score": 65.32140697218945,
|
| 972 |
-
"Standard Deviation": null,
|
| 973 |
-
"Rank": 14
|
| 974 |
-
}
|
| 975 |
-
}
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"config": {
|
| 979 |
-
"model_name": "claude-3-sonnet",
|
| 980 |
-
"organization": "Anthropic",
|
| 981 |
-
"license": "Proprietary",
|
| 982 |
-
"knowledge_cutoff": "2023/08"
|
| 983 |
-
},
|
| 984 |
-
"results": {
|
| 985 |
-
"OVERALL": {
|
| 986 |
-
"Average Score": 0.520010833,
|
| 987 |
-
"Standard Deviation": 0.005030563799,
|
| 988 |
-
"Rank": 17
|
| 989 |
-
},
|
| 990 |
-
"Geometry": {
|
| 991 |
-
"Average Score": 0.675613638,
|
| 992 |
-
"Standard Deviation": 0.05275594408,
|
| 993 |
-
"Rank": 15
|
| 994 |
-
},
|
| 995 |
-
"Algebra": {
|
| 996 |
-
"Average Score": 0.552025728,
|
| 997 |
-
"Standard Deviation": 0.04122192409,
|
| 998 |
-
"Rank": 23
|
| 999 |
-
},
|
| 1000 |
-
"Probability": {
|
| 1001 |
-
"Average Score": 0.516192848,
|
| 1002 |
-
"Standard Deviation": 0.04152293217,
|
| 1003 |
-
"Rank": 20
|
| 1004 |
-
},
|
| 1005 |
-
"Logical": {
|
| 1006 |
-
"Average Score": 0.588545747,
|
| 1007 |
-
"Standard Deviation": 0.06068211943,
|
| 1008 |
-
"Rank": 17
|
| 1009 |
-
},
|
| 1010 |
-
"Social": {
|
| 1011 |
-
"Average Score": 0.570437582,
|
| 1012 |
-
"Standard Deviation": 0.08607040862,
|
| 1013 |
-
"Rank": 15
|
| 1014 |
-
},
|
| 1015 |
-
"Chemistry": {
|
| 1016 |
-
"Average Score": 61.33538592327427,
|
| 1017 |
-
"Standard Deviation": null,
|
| 1018 |
-
"Rank": 16
|
| 1019 |
-
}
|
| 1020 |
-
}
|
| 1021 |
-
},
|
| 1022 |
-
{
|
| 1023 |
-
"config": {
|
| 1024 |
-
"model_name": "qwen1.5-14b-chat",
|
| 1025 |
-
"organization": "Alibaba",
|
| 1026 |
-
"license": "Qianwen LICENSE",
|
| 1027 |
-
"knowledge_cutoff": "2024/02"
|
| 1028 |
-
},
|
| 1029 |
-
"results": {
|
| 1030 |
-
"OVERALL": {
|
| 1031 |
-
"Average Score": 0.415328996,
|
| 1032 |
-
"Standard Deviation": 0.0743938717,
|
| 1033 |
-
"Rank": 28
|
| 1034 |
-
},
|
| 1035 |
-
"Geometry": {
|
| 1036 |
-
"Average Score": 0.452504016,
|
| 1037 |
-
"Standard Deviation": 0.04225594393,
|
| 1038 |
-
"Rank": 28
|
| 1039 |
-
},
|
| 1040 |
-
"Algebra": {
|
| 1041 |
-
"Average Score": 0.538655725,
|
| 1042 |
-
"Standard Deviation": 0.03721542594,
|
| 1043 |
-
"Rank": 24
|
| 1044 |
-
},
|
| 1045 |
-
"Probability": {
|
| 1046 |
-
"Average Score": 0.397185975,
|
| 1047 |
-
"Standard Deviation": 0.05607695946,
|
| 1048 |
-
"Rank": 30
|
| 1049 |
-
},
|
| 1050 |
-
"Logical": {
|
| 1051 |
-
"Average Score": 0.264573129,
|
| 1052 |
-
"Standard Deviation": 0.03936133174,
|
| 1053 |
-
"Rank": 35
|
| 1054 |
-
},
|
| 1055 |
-
"Social": {
|
| 1056 |
-
"Average Score": 0.287370142,
|
| 1057 |
-
"Standard Deviation": 0.04264085315,
|
| 1058 |
-
"Rank": 32
|
| 1059 |
-
},
|
| 1060 |
-
"Chemistry": {
|
| 1061 |
-
"Average Score": 38.552779976347026,
|
| 1062 |
-
"Standard Deviation": null,
|
| 1063 |
-
"Rank": 32
|
| 1064 |
-
}
|
| 1065 |
-
}
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"config": {
|
| 1069 |
-
"model_name": "claude-3-haiku",
|
| 1070 |
-
"organization": "Anthropic",
|
| 1071 |
-
"license": "Proprietary",
|
| 1072 |
-
"knowledge_cutoff": "2023/08"
|
| 1073 |
-
},
|
| 1074 |
-
"results": {
|
| 1075 |
-
"OVERALL": {
|
| 1076 |
-
"Average Score": 0.453901163,
|
| 1077 |
-
"Standard Deviation": 0.003604084261,
|
| 1078 |
-
"Rank": 24
|
| 1079 |
-
},
|
| 1080 |
-
"Geometry": {
|
| 1081 |
-
"Average Score": 0.607993912,
|
| 1082 |
-
"Standard Deviation": 0.05793460748,
|
| 1083 |
-
"Rank": 17
|
| 1084 |
-
},
|
| 1085 |
-
"Algebra": {
|
| 1086 |
-
"Average Score": 0.520054055,
|
| 1087 |
-
"Standard Deviation": 0.03333544511,
|
| 1088 |
-
"Rank": 25
|
| 1089 |
-
},
|
| 1090 |
-
"Probability": {
|
| 1091 |
-
"Average Score": 0.474460688,
|
| 1092 |
-
"Standard Deviation": 0.0446501933,
|
| 1093 |
-
"Rank": 25
|
| 1094 |
-
},
|
| 1095 |
-
"Logical": {
|
| 1096 |
-
"Average Score": 0.512815976,
|
| 1097 |
-
"Standard Deviation": 0.0163264281,
|
| 1098 |
-
"Rank": 21
|
| 1099 |
-
},
|
| 1100 |
-
"Social": {
|
| 1101 |
-
"Average Score": 0.551083976,
|
| 1102 |
-
"Standard Deviation": 0.05374722539,
|
| 1103 |
-
"Rank": 17
|
| 1104 |
-
},
|
| 1105 |
-
"Chemistry": {
|
| 1106 |
-
"Average Score": 56.40200048817984,
|
| 1107 |
-
"Standard Deviation": null,
|
| 1108 |
-
"Rank": 17
|
| 1109 |
-
}
|
| 1110 |
-
}
|
| 1111 |
-
},
|
| 1112 |
-
{
|
| 1113 |
-
"config": {
|
| 1114 |
-
"model_name": "claude-2.1",
|
| 1115 |
-
"organization": "Anthropic",
|
| 1116 |
-
"license": "Proprietary",
|
| 1117 |
-
"knowledge_cutoff": "Unknown"
|
| 1118 |
-
},
|
| 1119 |
-
"results": {
|
| 1120 |
-
"OVERALL": {
|
| 1121 |
-
"Average Score": 0.35814708,
|
| 1122 |
-
"Standard Deviation": 0.09168134168,
|
| 1123 |
-
"Rank": 36
|
| 1124 |
-
},
|
| 1125 |
-
"Geometry": {
|
| 1126 |
-
"Average Score": 0.62752395,
|
| 1127 |
-
"Standard Deviation": 0.07232659398,
|
| 1128 |
-
"Rank": 16
|
| 1129 |
-
},
|
| 1130 |
-
"Algebra": {
|
| 1131 |
-
"Average Score": 0.508849609,
|
| 1132 |
-
"Standard Deviation": 0.0346897465,
|
| 1133 |
-
"Rank": 26
|
| 1134 |
-
},
|
| 1135 |
-
"Probability": {
|
| 1136 |
-
"Average Score": 0.41477086,
|
| 1137 |
-
"Standard Deviation": 0.05964060239,
|
| 1138 |
-
"Rank": 29
|
| 1139 |
-
},
|
| 1140 |
-
"Logical": {
|
| 1141 |
-
"Average Score": 0.482923674,
|
| 1142 |
-
"Standard Deviation": 0.01989147048,
|
| 1143 |
-
"Rank": 22
|
| 1144 |
-
},
|
| 1145 |
-
"Social": {
|
| 1146 |
-
"Average Score": 0.333804568,
|
| 1147 |
-
"Standard Deviation": 0.03775548253,
|
| 1148 |
-
"Rank": 29
|
| 1149 |
-
},
|
| 1150 |
-
"Chemistry": {
|
| 1151 |
-
"Average Score": 47.23672563994903,
|
| 1152 |
-
"Standard Deviation": null,
|
| 1153 |
-
"Rank": 22
|
| 1154 |
-
}
|
| 1155 |
-
}
|
| 1156 |
-
},
|
| 1157 |
-
{
|
| 1158 |
-
"config": {
|
| 1159 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 1160 |
-
"organization": "Mistral",
|
| 1161 |
-
"license": "Apache 2.0",
|
| 1162 |
-
"knowledge_cutoff": "2023/12"
|
| 1163 |
-
},
|
| 1164 |
-
"results": {
|
| 1165 |
-
"OVERALL": {
|
| 1166 |
-
"Average Score": 0.382659161,
|
| 1167 |
-
"Standard Deviation": 0.07594496929,
|
| 1168 |
-
"Rank": 31
|
| 1169 |
-
},
|
| 1170 |
-
"Geometry": {
|
| 1171 |
-
"Average Score": 0.432216097,
|
| 1172 |
-
"Standard Deviation": 0.04747949254,
|
| 1173 |
-
"Rank": 31
|
| 1174 |
-
},
|
| 1175 |
-
"Algebra": {
|
| 1176 |
-
"Average Score": 0.478314888,
|
| 1177 |
-
"Standard Deviation": 0.01998797419,
|
| 1178 |
-
"Rank": 27
|
| 1179 |
-
},
|
| 1180 |
-
"Probability": {
|
| 1181 |
-
"Average Score": 0.427144725,
|
| 1182 |
-
"Standard Deviation": 0.0590923329,
|
| 1183 |
-
"Rank": 28
|
| 1184 |
-
},
|
| 1185 |
-
"Logical": {
|
| 1186 |
-
"Average Score": 0.340041983,
|
| 1187 |
-
"Standard Deviation": 0.008397574592,
|
| 1188 |
-
"Rank": 28
|
| 1189 |
-
},
|
| 1190 |
-
"Social": {
|
| 1191 |
-
"Average Score": 0.251949622,
|
| 1192 |
-
"Standard Deviation": 0.03346674405,
|
| 1193 |
-
"Rank": 37
|
| 1194 |
-
},
|
| 1195 |
-
"Chemistry": {
|
| 1196 |
-
"Average Score": 44.533118241976666,
|
| 1197 |
-
"Standard Deviation": null,
|
| 1198 |
-
"Rank": 26
|
| 1199 |
-
}
|
| 1200 |
-
}
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"config": {
|
| 1204 |
-
"model_name": "claude-2.0",
|
| 1205 |
-
"organization": "Anthropic",
|
| 1206 |
-
"license": "Proprietary",
|
| 1207 |
-
"knowledge_cutoff": "Unknown"
|
| 1208 |
-
},
|
| 1209 |
-
"results": {
|
| 1210 |
-
"OVERALL": {
|
| 1211 |
-
"Average Score": 0.322718057,
|
| 1212 |
-
"Standard Deviation": 0.08369883584,
|
| 1213 |
-
"Rank": 38
|
| 1214 |
-
},
|
| 1215 |
-
"Geometry": {
|
| 1216 |
-
"Average Score": 0.604141967,
|
| 1217 |
-
"Standard Deviation": 0.05116441826,
|
| 1218 |
-
"Rank": 18
|
| 1219 |
-
},
|
| 1220 |
-
"Algebra": {
|
| 1221 |
-
"Average Score": 0.474350734,
|
| 1222 |
-
"Standard Deviation": 0.01510393066,
|
| 1223 |
-
"Rank": 28
|
| 1224 |
-
},
|
| 1225 |
-
"Probability": {
|
| 1226 |
-
"Average Score": 0.437950412,
|
| 1227 |
-
"Standard Deviation": 0.05985594317,
|
| 1228 |
-
"Rank": 27
|
| 1229 |
-
},
|
| 1230 |
-
"Logical": {
|
| 1231 |
-
"Average Score": 0.445620646,
|
| 1232 |
-
"Standard Deviation": 0.01812614805,
|
| 1233 |
-
"Rank": 24
|
| 1234 |
-
},
|
| 1235 |
-
"Social": {
|
| 1236 |
-
"Average Score": 0.469422836,
|
| 1237 |
-
"Standard Deviation": 0.05999901796,
|
| 1238 |
-
"Rank": 21
|
| 1239 |
-
},
|
| 1240 |
-
"Chemistry": {
|
| 1241 |
-
"Average Score": 50.773143448036464,
|
| 1242 |
-
"Standard Deviation": null,
|
| 1243 |
-
"Rank": 20
|
| 1244 |
-
}
|
| 1245 |
-
}
|
| 1246 |
-
},
|
| 1247 |
-
{
|
| 1248 |
-
"config": {
|
| 1249 |
-
"model_name": "starling-lm-7b-beta",
|
| 1250 |
-
"organization": "Nexusflow",
|
| 1251 |
-
"license": "Apache-2.0",
|
| 1252 |
-
"knowledge_cutoff": "2024/03"
|
| 1253 |
-
},
|
| 1254 |
-
"results": {
|
| 1255 |
-
"OVERALL": {
|
| 1256 |
-
"Average Score": 0.479391856,
|
| 1257 |
-
"Standard Deviation": 0.04199990887,
|
| 1258 |
-
"Rank": 22
|
| 1259 |
-
},
|
| 1260 |
-
"Geometry": {
|
| 1261 |
-
"Average Score": 0.446654388,
|
| 1262 |
-
"Standard Deviation": 0.05637864999,
|
| 1263 |
-
"Rank": 30
|
| 1264 |
-
},
|
| 1265 |
-
"Algebra": {
|
| 1266 |
-
"Average Score": 0.473952749,
|
| 1267 |
-
"Standard Deviation": 0.01584301288,
|
| 1268 |
-
"Rank": 29
|
| 1269 |
-
},
|
| 1270 |
-
"Probability": {
|
| 1271 |
-
"Average Score": 0.395197837,
|
| 1272 |
-
"Standard Deviation": 0.05814798892,
|
| 1273 |
-
"Rank": 31
|
| 1274 |
-
},
|
| 1275 |
-
"Logical": {
|
| 1276 |
-
"Average Score": 0.39927199,
|
| 1277 |
-
"Standard Deviation": 0.02125277518,
|
| 1278 |
-
"Rank": 26
|
| 1279 |
-
},
|
| 1280 |
-
"Social": {
|
| 1281 |
-
"Average Score": 0.380021662,
|
| 1282 |
-
"Standard Deviation": 0.04622452748,
|
| 1283 |
-
"Rank": 27
|
| 1284 |
-
},
|
| 1285 |
-
"Chemistry": {
|
| 1286 |
-
"Average Score": 38.27587102395908,
|
| 1287 |
-
"Standard Deviation": null,
|
| 1288 |
-
"Rank": 33
|
| 1289 |
-
}
|
| 1290 |
-
}
|
| 1291 |
-
},
|
| 1292 |
-
{
|
| 1293 |
-
"config": {
|
| 1294 |
-
"model_name": "gemini-1.0-pro-001",
|
| 1295 |
-
"organization": "Google",
|
| 1296 |
-
"license": "Proprietary",
|
| 1297 |
-
"knowledge_cutoff": "2023/04"
|
| 1298 |
-
},
|
| 1299 |
-
"results": {
|
| 1300 |
-
"OVERALL": {
|
| 1301 |
-
"Average Score": 0.449040654,
|
| 1302 |
-
"Standard Deviation": 0.0450610177,
|
| 1303 |
-
"Rank": 25
|
| 1304 |
-
},
|
| 1305 |
-
"Geometry": {
|
| 1306 |
-
"Average Score": 0.578347959,
|
| 1307 |
-
"Standard Deviation": 0.04242873607,
|
| 1308 |
-
"Rank": 21
|
| 1309 |
-
},
|
| 1310 |
-
"Algebra": {
|
| 1311 |
-
"Average Score": 0.462417786,
|
| 1312 |
-
"Standard Deviation": 0.01668313635,
|
| 1313 |
-
"Rank": 30
|
| 1314 |
-
},
|
| 1315 |
-
"Probability": {
|
| 1316 |
-
"Average Score": 0.289836324,
|
| 1317 |
-
"Standard Deviation": 0.05739831115,
|
| 1318 |
-
"Rank": 39
|
| 1319 |
-
},
|
| 1320 |
-
"Logical": {
|
| 1321 |
-
"Average Score": 0.191140355,
|
| 1322 |
-
"Standard Deviation": 0.03394652499,
|
| 1323 |
-
"Rank": 41
|
| 1324 |
-
},
|
| 1325 |
-
"Social": {
|
| 1326 |
-
"Average Score": 0.130790863,
|
| 1327 |
-
"Standard Deviation": 0.02800188173,
|
| 1328 |
-
"Rank": 47
|
| 1329 |
-
},
|
| 1330 |
-
"Chemistry": {
|
| 1331 |
-
"Average Score": 45.22204471452975,
|
| 1332 |
-
"Standard Deviation": null,
|
| 1333 |
-
"Rank": 24
|
| 1334 |
-
}
|
| 1335 |
-
}
|
| 1336 |
-
},
|
| 1337 |
-
{
|
| 1338 |
-
"config": {
|
| 1339 |
-
"model_name": "openchat-3.5-0106",
|
| 1340 |
-
"organization": "OpenChat",
|
| 1341 |
-
"license": "Apache-2.0",
|
| 1342 |
-
"knowledge_cutoff": "2024/01"
|
| 1343 |
-
},
|
| 1344 |
-
"results": {
|
| 1345 |
-
"OVERALL": {
|
| 1346 |
-
"Average Score": 0.363929888,
|
| 1347 |
-
"Standard Deviation": 0.08602347145,
|
| 1348 |
-
"Rank": 34
|
| 1349 |
-
},
|
| 1350 |
-
"Geometry": {
|
| 1351 |
-
"Average Score": 0.38715246,
|
| 1352 |
-
"Standard Deviation": 0.03701851946,
|
| 1353 |
-
"Rank": 34
|
| 1354 |
-
},
|
| 1355 |
-
"Algebra": {
|
| 1356 |
-
"Average Score": 0.441233712,
|
| 1357 |
-
"Standard Deviation": 0.01135753754,
|
| 1358 |
-
"Rank": 31
|
| 1359 |
-
},
|
| 1360 |
-
"Probability": {
|
| 1361 |
-
"Average Score": 0.38802618,
|
| 1362 |
-
"Standard Deviation": 0.05663879714,
|
| 1363 |
-
"Rank": 32
|
| 1364 |
-
},
|
| 1365 |
-
"Logical": {
|
| 1366 |
-
"Average Score": 0.336754383,
|
| 1367 |
-
"Standard Deviation": 0.01608478079,
|
| 1368 |
-
"Rank": 29
|
| 1369 |
-
},
|
| 1370 |
-
"Social": {
|
| 1371 |
-
"Average Score": 0.250891608,
|
| 1372 |
-
"Standard Deviation": 0.03253769914,
|
| 1373 |
-
"Rank": 38
|
| 1374 |
-
},
|
| 1375 |
-
"Chemistry": {
|
| 1376 |
-
"Average Score": 33.70639271807677,
|
| 1377 |
-
"Standard Deviation": null,
|
| 1378 |
-
"Rank": 34
|
| 1379 |
-
}
|
| 1380 |
-
}
|
| 1381 |
-
},
|
| 1382 |
-
{
|
| 1383 |
-
"config": {
|
| 1384 |
-
"model_name": "openchat-3.5",
|
| 1385 |
-
"organization": "OpenChat",
|
| 1386 |
-
"license": "Apache-2.0",
|
| 1387 |
-
"knowledge_cutoff": "2023/11"
|
| 1388 |
-
},
|
| 1389 |
-
"results": {
|
| 1390 |
-
"OVERALL": {
|
| 1391 |
-
"Average Score": 0.361341296,
|
| 1392 |
-
"Standard Deviation": 0.09034869493,
|
| 1393 |
-
"Rank": 35
|
| 1394 |
-
},
|
| 1395 |
-
"Geometry": {
|
| 1396 |
-
"Average Score": 0.401699069,
|
| 1397 |
-
"Standard Deviation": 0.03410726557,
|
| 1398 |
-
"Rank": 32
|
| 1399 |
-
},
|
| 1400 |
-
"Algebra": {
|
| 1401 |
-
"Average Score": 0.414095336,
|
| 1402 |
-
"Standard Deviation": 0.01881964261,
|
| 1403 |
-
"Rank": 33
|
| 1404 |
-
},
|
| 1405 |
-
"Probability": {
|
| 1406 |
-
"Average Score": 0.349601002,
|
| 1407 |
-
"Standard Deviation": 0.05077455539,
|
| 1408 |
-
"Rank": 34
|
| 1409 |
-
},
|
| 1410 |
-
"Logical": {
|
| 1411 |
-
"Average Score": 0.331069242,
|
| 1412 |
-
"Standard Deviation": 0.02180827173,
|
| 1413 |
-
"Rank": 31
|
| 1414 |
-
},
|
| 1415 |
-
"Social": {
|
| 1416 |
-
"Average Score": 0.319991655,
|
| 1417 |
-
"Standard Deviation": 0.04502478724,
|
| 1418 |
-
"Rank": 31
|
| 1419 |
-
},
|
| 1420 |
-
"Chemistry": {
|
| 1421 |
-
"Average Score": 33.020911255646965,
|
| 1422 |
-
"Standard Deviation": null,
|
| 1423 |
-
"Rank": 35
|
| 1424 |
-
}
|
| 1425 |
-
}
|
| 1426 |
-
},
|
| 1427 |
-
{
|
| 1428 |
-
"config": {
|
| 1429 |
-
"model_name": "command-r-(08-2024)",
|
| 1430 |
-
"organization": "Cohere",
|
| 1431 |
-
"license": "CC-BY-NC-4.0",
|
| 1432 |
-
"knowledge_cutoff": "2024/08"
|
| 1433 |
-
},
|
| 1434 |
-
"results": {
|
| 1435 |
-
"OVERALL": {
|
| 1436 |
-
"Average Score": 0.427605298,
|
| 1437 |
-
"Standard Deviation": 0.01747449163,
|
| 1438 |
-
"Rank": 26
|
| 1439 |
-
},
|
| 1440 |
-
"Geometry": {
|
| 1441 |
-
"Average Score": 0.448300727,
|
| 1442 |
-
"Standard Deviation": 0.04996362328,
|
| 1443 |
-
"Rank": 29
|
| 1444 |
-
},
|
| 1445 |
-
"Algebra": {
|
| 1446 |
-
"Average Score": 0.417519167,
|
| 1447 |
-
"Standard Deviation": 0.01822196902,
|
| 1448 |
-
"Rank": 32
|
| 1449 |
-
},
|
| 1450 |
-
"Probability": {
|
| 1451 |
-
"Average Score": 0.366336281,
|
| 1452 |
-
"Standard Deviation": 0.04716826942,
|
| 1453 |
-
"Rank": 33
|
| 1454 |
-
},
|
| 1455 |
-
"Logical": {
|
| 1456 |
-
"Average Score": 0.214657906,
|
| 1457 |
-
"Standard Deviation": 0.03003579835,
|
| 1458 |
-
"Rank": 38
|
| 1459 |
-
},
|
| 1460 |
-
"Social": {
|
| 1461 |
-
"Average Score": 0.276088379,
|
| 1462 |
-
"Standard Deviation": 0.03295234688,
|
| 1463 |
-
"Rank": 34
|
| 1464 |
-
},
|
| 1465 |
-
"Chemistry": {
|
| 1466 |
-
"Average Score": 39.61492485677676,
|
| 1467 |
-
"Standard Deviation": null,
|
| 1468 |
-
"Rank": 31
|
| 1469 |
-
}
|
| 1470 |
-
}
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"config": {
|
| 1474 |
-
"model_name": "gemma-1.1-7b-it",
|
| 1475 |
-
"organization": "Google",
|
| 1476 |
-
"license": "Gemma License",
|
| 1477 |
-
"knowledge_cutoff": "2024/02"
|
| 1478 |
-
},
|
| 1479 |
-
"results": {
|
| 1480 |
-
"OVERALL": {
|
| 1481 |
-
"Average Score": 0.339506922,
|
| 1482 |
-
"Standard Deviation": 0.1066279108,
|
| 1483 |
-
"Rank": 37
|
| 1484 |
-
},
|
| 1485 |
-
"Geometry": {
|
| 1486 |
-
"Average Score": 0.324170977,
|
| 1487 |
-
"Standard Deviation": 0.04668553765,
|
| 1488 |
-
"Rank": 37
|
| 1489 |
-
},
|
| 1490 |
-
"Algebra": {
|
| 1491 |
-
"Average Score": 0.398684697,
|
| 1492 |
-
"Standard Deviation": 0.01982398259,
|
| 1493 |
-
"Rank": 34
|
| 1494 |
-
},
|
| 1495 |
-
"Probability": {
|
| 1496 |
-
"Average Score": 0.293253175,
|
| 1497 |
-
"Standard Deviation": 0.05126192191,
|
| 1498 |
-
"Rank": 38
|
| 1499 |
-
},
|
| 1500 |
-
"Logical": {
|
| 1501 |
-
"Average Score": 0.317750796,
|
| 1502 |
-
"Standard Deviation": 0.01101933543,
|
| 1503 |
-
"Rank": 32
|
| 1504 |
-
},
|
| 1505 |
-
"Social": {
|
| 1506 |
-
"Average Score": 0.179073276,
|
| 1507 |
-
"Standard Deviation": 0.02009658805,
|
| 1508 |
-
"Rank": 43
|
| 1509 |
-
},
|
| 1510 |
-
"Chemistry": {
|
| 1511 |
-
"Average Score": 42.666504105798204,
|
| 1512 |
-
"Standard Deviation": null,
|
| 1513 |
-
"Rank": 28
|
| 1514 |
-
}
|
| 1515 |
-
}
|
| 1516 |
-
},
|
| 1517 |
-
{
|
| 1518 |
-
"config": {
|
| 1519 |
-
"model_name": "llama3-8b-instruct",
|
| 1520 |
-
"organization": "Meta",
|
| 1521 |
-
"license": "Llama 3 Community",
|
| 1522 |
-
"knowledge_cutoff": "2023/03"
|
| 1523 |
-
},
|
| 1524 |
-
"results": {
|
| 1525 |
-
"OVERALL": {
|
| 1526 |
-
"Average Score": 0.367722676,
|
| 1527 |
-
"Standard Deviation": 0.1071368221,
|
| 1528 |
-
"Rank": 32
|
| 1529 |
-
},
|
| 1530 |
-
"Geometry": {
|
| 1531 |
-
"Average Score": 0.367143758,
|
| 1532 |
-
"Standard Deviation": 0.04363680358,
|
| 1533 |
-
"Rank": 35
|
| 1534 |
-
},
|
| 1535 |
-
"Algebra": {
|
| 1536 |
-
"Average Score": 0.391480973,
|
| 1537 |
-
"Standard Deviation": 0.02757445266,
|
| 1538 |
-
"Rank": 35
|
| 1539 |
-
},
|
| 1540 |
-
"Probability": {
|
| 1541 |
-
"Average Score": 0.317616445,
|
| 1542 |
-
"Standard Deviation": 0.04300430361,
|
| 1543 |
-
"Rank": 37
|
| 1544 |
-
},
|
| 1545 |
-
"Logical": {
|
| 1546 |
-
"Average Score": 0.461607495,
|
| 1547 |
-
"Standard Deviation": 0.02185028842,
|
| 1548 |
-
"Rank": 23
|
| 1549 |
-
},
|
| 1550 |
-
"Social": {
|
| 1551 |
-
"Average Score": 0.336373622,
|
| 1552 |
-
"Standard Deviation": 0.05762408512,
|
| 1553 |
-
"Rank": 28
|
| 1554 |
-
},
|
| 1555 |
-
"Chemistry": {
|
| 1556 |
-
"Average Score": 45.35392139264795,
|
| 1557 |
-
"Standard Deviation": null,
|
| 1558 |
-
"Rank": 23
|
| 1559 |
-
}
|
| 1560 |
-
}
|
| 1561 |
-
},
|
| 1562 |
-
{
|
| 1563 |
-
"config": {
|
| 1564 |
-
"model_name": "gemma-2-2b-it",
|
| 1565 |
-
"organization": "Google",
|
| 1566 |
-
"license": "Gemma License",
|
| 1567 |
-
"knowledge_cutoff": "2024/07"
|
| 1568 |
-
},
|
| 1569 |
-
"results": {
|
| 1570 |
-
"OVERALL": {
|
| 1571 |
-
"Average Score": 0.502167612,
|
| 1572 |
-
"Standard Deviation": 0.04389786763,
|
| 1573 |
-
"Rank": 20
|
| 1574 |
-
},
|
| 1575 |
-
"Geometry": {
|
| 1576 |
-
"Average Score": 0.395006676,
|
| 1577 |
-
"Standard Deviation": 0.05882607713,
|
| 1578 |
-
"Rank": 33
|
| 1579 |
-
},
|
| 1580 |
-
"Algebra": {
|
| 1581 |
-
"Average Score": 0.379391887,
|
| 1582 |
-
"Standard Deviation": 0.01722410785,
|
| 1583 |
-
"Rank": 36
|
| 1584 |
-
},
|
| 1585 |
-
"Probability": {
|
| 1586 |
-
"Average Score": 0.331231097,
|
| 1587 |
-
"Standard Deviation": 0.05392499987,
|
| 1588 |
-
"Rank": 36
|
| 1589 |
-
},
|
| 1590 |
-
"Logical": {
|
| 1591 |
-
"Average Score": 0.367687789,
|
| 1592 |
-
"Standard Deviation": 0.02547968808,
|
| 1593 |
-
"Rank": 27
|
| 1594 |
-
},
|
| 1595 |
-
"Social": {
|
| 1596 |
-
"Average Score": 0.393482094,
|
| 1597 |
-
"Standard Deviation": 0.06450214024,
|
| 1598 |
-
"Rank": 25
|
| 1599 |
-
},
|
| 1600 |
-
"Chemistry": {
|
| 1601 |
-
"Average Score": 30.53406933106768,
|
| 1602 |
-
"Standard Deviation": null,
|
| 1603 |
-
"Rank": 37
|
| 1604 |
-
}
|
| 1605 |
-
}
|
| 1606 |
-
},
|
| 1607 |
-
{
|
| 1608 |
-
"config": {
|
| 1609 |
-
"model_name": "starling-lm-7b-alpha",
|
| 1610 |
-
"organization": "Nexusflow",
|
| 1611 |
-
"license": "Apache-2.0",
|
| 1612 |
-
"knowledge_cutoff": "2023/11"
|
| 1613 |
-
},
|
| 1614 |
-
"results": {
|
| 1615 |
-
"OVERALL": {
|
| 1616 |
-
"Average Score": 0.366628765,
|
| 1617 |
-
"Standard Deviation": 0.08405492929,
|
| 1618 |
-
"Rank": 33
|
| 1619 |
-
},
|
| 1620 |
-
"Geometry": {
|
| 1621 |
-
"Average Score": 0.336782578,
|
| 1622 |
-
"Standard Deviation": 0.04069449132,
|
| 1623 |
-
"Rank": 36
|
| 1624 |
-
},
|
| 1625 |
-
"Algebra": {
|
| 1626 |
-
"Average Score": 0.371551932,
|
| 1627 |
-
"Standard Deviation": 0.03367241745,
|
| 1628 |
-
"Rank": 37
|
| 1629 |
-
},
|
| 1630 |
-
"Probability": {
|
| 1631 |
-
"Average Score": 0.331472505,
|
| 1632 |
-
"Standard Deviation": 0.04833324282,
|
| 1633 |
-
"Rank": 35
|
| 1634 |
-
},
|
| 1635 |
-
"Logical": {
|
| 1636 |
-
"Average Score": 0.260869624,
|
| 1637 |
-
"Standard Deviation": 0.03562735237,
|
| 1638 |
-
"Rank": 36
|
| 1639 |
-
},
|
| 1640 |
-
"Social": {
|
| 1641 |
-
"Average Score": 0.271975534,
|
| 1642 |
-
"Standard Deviation": 0.04266753408,
|
| 1643 |
-
"Rank": 35
|
| 1644 |
-
},
|
| 1645 |
-
"Chemistry": {
|
| 1646 |
-
"Average Score": 30.07926487356878,
|
| 1647 |
-
"Standard Deviation": null,
|
| 1648 |
-
"Rank": 38
|
| 1649 |
-
}
|
| 1650 |
-
}
|
| 1651 |
-
},
|
| 1652 |
-
{
|
| 1653 |
-
"config": {
|
| 1654 |
-
"model_name": "qwen1.5-4b-chat",
|
| 1655 |
-
"organization": "Alibaba",
|
| 1656 |
-
"license": "Qianwen LICENSE",
|
| 1657 |
-
"knowledge_cutoff": "2024/02"
|
| 1658 |
-
},
|
| 1659 |
-
"results": {
|
| 1660 |
-
"OVERALL": {
|
| 1661 |
-
"Average Score": 0.111876411,
|
| 1662 |
-
"Standard Deviation": 0.04241022785,
|
| 1663 |
-
"Rank": 49
|
| 1664 |
-
},
|
| 1665 |
-
"Geometry": {
|
| 1666 |
-
"Average Score": 0.215834522,
|
| 1667 |
-
"Standard Deviation": 0.0363766363,
|
| 1668 |
-
"Rank": 41
|
| 1669 |
-
},
|
| 1670 |
-
"Algebra": {
|
| 1671 |
-
"Average Score": 0.305589811,
|
| 1672 |
-
"Standard Deviation": 0.02354198912,
|
| 1673 |
-
"Rank": 38
|
| 1674 |
-
},
|
| 1675 |
-
"Probability": {
|
| 1676 |
-
"Average Score": 0.149365327,
|
| 1677 |
-
"Standard Deviation": 0.03489672675,
|
| 1678 |
-
"Rank": 45
|
| 1679 |
-
},
|
| 1680 |
-
"Logical": {
|
| 1681 |
-
"Average Score": 0.116210168,
|
| 1682 |
-
"Standard Deviation": 0.005927966496,
|
| 1683 |
-
"Rank": 47
|
| 1684 |
-
},
|
| 1685 |
-
"Social": {
|
| 1686 |
-
"Average Score": 0.18195615,
|
| 1687 |
-
"Standard Deviation": 0.02269805277,
|
| 1688 |
-
"Rank": 42
|
| 1689 |
-
},
|
| 1690 |
-
"Chemistry": {
|
| 1691 |
-
"Average Score": 13.21208067122554,
|
| 1692 |
-
"Standard Deviation": null,
|
| 1693 |
-
"Rank": 48
|
| 1694 |
-
}
|
| 1695 |
-
}
|
| 1696 |
-
},
|
| 1697 |
-
{
|
| 1698 |
-
"config": {
|
| 1699 |
-
"model_name": "command-r-(04-2024)",
|
| 1700 |
-
"organization": "Cohere",
|
| 1701 |
-
"license": "CC-BY-NC-4.0",
|
| 1702 |
-
"knowledge_cutoff": "2024/04"
|
| 1703 |
-
},
|
| 1704 |
-
"results": {
|
| 1705 |
-
"OVERALL": {
|
| 1706 |
-
"Average Score": 0.388783887,
|
| 1707 |
-
"Standard Deviation": 0.07417186783,
|
| 1708 |
-
"Rank": 30
|
| 1709 |
-
},
|
| 1710 |
-
"Geometry": {
|
| 1711 |
-
"Average Score": 0.300416698,
|
| 1712 |
-
"Standard Deviation": 0.03485612736,
|
| 1713 |
-
"Rank": 38
|
| 1714 |
-
},
|
| 1715 |
-
"Algebra": {
|
| 1716 |
-
"Average Score": 0.293120231,
|
| 1717 |
-
"Standard Deviation": 0.032926484,
|
| 1718 |
-
"Rank": 39
|
| 1719 |
-
},
|
| 1720 |
-
"Probability": {
|
| 1721 |
-
"Average Score": 0.281271304,
|
| 1722 |
-
"Standard Deviation": 0.05697149867,
|
| 1723 |
-
"Rank": 40
|
| 1724 |
-
},
|
| 1725 |
-
"Logical": {
|
| 1726 |
-
"Average Score": 0.276189906,
|
| 1727 |
-
"Standard Deviation": 0.03562914754,
|
| 1728 |
-
"Rank": 34
|
| 1729 |
-
},
|
| 1730 |
-
"Social": {
|
| 1731 |
-
"Average Score": 0.283882949,
|
| 1732 |
-
"Standard Deviation": 0.03336901148,
|
| 1733 |
-
"Rank": 33
|
| 1734 |
-
},
|
| 1735 |
-
"Chemistry": {
|
| 1736 |
-
"Average Score": 41.346336503003236,
|
| 1737 |
-
"Standard Deviation": null,
|
| 1738 |
-
"Rank": 29
|
| 1739 |
-
}
|
| 1740 |
-
}
|
| 1741 |
-
},
|
| 1742 |
-
{
|
| 1743 |
-
"config": {
|
| 1744 |
-
"model_name": "vicuna-33b",
|
| 1745 |
-
"organization": "LMSYS",
|
| 1746 |
-
"license": "Non-commercial",
|
| 1747 |
-
"knowledge_cutoff": "2023/08"
|
| 1748 |
-
},
|
| 1749 |
-
"results": {
|
| 1750 |
-
"OVERALL": {
|
| 1751 |
-
"Average Score": 0.316543555,
|
| 1752 |
-
"Standard Deviation": 0.08922095647,
|
| 1753 |
-
"Rank": 39
|
| 1754 |
-
},
|
| 1755 |
-
"Geometry": {
|
| 1756 |
-
"Average Score": 0.208284679,
|
| 1757 |
-
"Standard Deviation": 0.03937771461,
|
| 1758 |
-
"Rank": 42
|
| 1759 |
-
},
|
| 1760 |
-
"Algebra": {
|
| 1761 |
-
"Average Score": 0.248994048,
|
| 1762 |
-
"Standard Deviation": 0.02668175054,
|
| 1763 |
-
"Rank": 41
|
| 1764 |
-
},
|
| 1765 |
-
"Probability": {
|
| 1766 |
-
"Average Score": 0.222313995,
|
| 1767 |
-
"Standard Deviation": 0.03978859759,
|
| 1768 |
-
"Rank": 43
|
| 1769 |
-
},
|
| 1770 |
-
"Logical": {
|
| 1771 |
-
"Average Score": 0.180291222,
|
| 1772 |
-
"Standard Deviation": 0.021886267,
|
| 1773 |
-
"Rank": 42
|
| 1774 |
-
},
|
| 1775 |
-
"Social": {
|
| 1776 |
-
"Average Score": 0.257623798,
|
| 1777 |
-
"Standard Deviation": 0.02653724437,
|
| 1778 |
-
"Rank": 36
|
| 1779 |
-
},
|
| 1780 |
-
"Chemistry": {
|
| 1781 |
-
"Average Score": 28.01838653090379,
|
| 1782 |
-
"Standard Deviation": null,
|
| 1783 |
-
"Rank": 39
|
| 1784 |
-
}
|
| 1785 |
-
}
|
| 1786 |
-
},
|
| 1787 |
-
{
|
| 1788 |
-
"config": {
|
| 1789 |
-
"model_name": "gemma-7b-it",
|
| 1790 |
-
"organization": "Google",
|
| 1791 |
-
"license": "Gemma License",
|
| 1792 |
-
"knowledge_cutoff": "2024/02"
|
| 1793 |
-
},
|
| 1794 |
-
"results": {
|
| 1795 |
-
"OVERALL": {
|
| 1796 |
-
"Average Score": 0.285077558,
|
| 1797 |
-
"Standard Deviation": 0.08871758453,
|
| 1798 |
-
"Rank": 41
|
| 1799 |
-
},
|
| 1800 |
-
"Geometry": {
|
| 1801 |
-
"Average Score": 0.244791417,
|
| 1802 |
-
"Standard Deviation": 0.0289612078,
|
| 1803 |
-
"Rank": 39
|
| 1804 |
-
},
|
| 1805 |
-
"Algebra": {
|
| 1806 |
-
"Average Score": 0.250614794,
|
| 1807 |
-
"Standard Deviation": 0.01991678295,
|
| 1808 |
-
"Rank": 40
|
| 1809 |
-
},
|
| 1810 |
-
"Probability": {
|
| 1811 |
-
"Average Score": 0.174313053,
|
| 1812 |
-
"Standard Deviation": 0.03765424728,
|
| 1813 |
-
"Rank": 44
|
| 1814 |
-
},
|
| 1815 |
-
"Logical": {
|
| 1816 |
-
"Average Score": 0.197505536,
|
| 1817 |
-
"Standard Deviation": 0.02050298885,
|
| 1818 |
-
"Rank": 39
|
| 1819 |
-
},
|
| 1820 |
-
"Social": {
|
| 1821 |
-
"Average Score": 0.202138025,
|
| 1822 |
-
"Standard Deviation": 0.02098346639,
|
| 1823 |
-
"Rank": 41
|
| 1824 |
-
},
|
| 1825 |
-
"Chemistry": {
|
| 1826 |
-
"Average Score": 28.014658234926813,
|
| 1827 |
-
"Standard Deviation": null,
|
| 1828 |
-
"Rank": 40
|
| 1829 |
-
}
|
| 1830 |
-
}
|
| 1831 |
-
},
|
| 1832 |
-
{
|
| 1833 |
-
"config": {
|
| 1834 |
-
"model_name": "mistral-7b-instruct-2",
|
| 1835 |
-
"organization": "Mistral",
|
| 1836 |
-
"license": "Apache 2.0",
|
| 1837 |
-
"knowledge_cutoff": "2023/12"
|
| 1838 |
-
},
|
| 1839 |
-
"results": {
|
| 1840 |
-
"OVERALL": {
|
| 1841 |
-
"Average Score": 0.427513868,
|
| 1842 |
-
"Standard Deviation": 0.05553921135,
|
| 1843 |
-
"Rank": 27
|
| 1844 |
-
},
|
| 1845 |
-
"Geometry": {
|
| 1846 |
-
"Average Score": 0.216402626,
|
| 1847 |
-
"Standard Deviation": 0.03338414918,
|
| 1848 |
-
"Rank": 40
|
| 1849 |
-
},
|
| 1850 |
-
"Algebra": {
|
| 1851 |
-
"Average Score": 0.233777838,
|
| 1852 |
-
"Standard Deviation": 0.0155226054,
|
| 1853 |
-
"Rank": 42
|
| 1854 |
-
},
|
| 1855 |
-
"Probability": {
|
| 1856 |
-
"Average Score": 0.25118175,
|
| 1857 |
-
"Standard Deviation": 0.04065514593,
|
| 1858 |
-
"Rank": 41
|
| 1859 |
-
},
|
| 1860 |
-
"Logical": {
|
| 1861 |
-
"Average Score": 0.224469136,
|
| 1862 |
-
"Standard Deviation": 0.03404706752,
|
| 1863 |
-
"Rank": 37
|
| 1864 |
-
},
|
| 1865 |
-
"Social": {
|
| 1866 |
-
"Average Score": 0.209386782,
|
| 1867 |
-
"Standard Deviation": 0.02738569921,
|
| 1868 |
-
"Rank": 40
|
| 1869 |
-
},
|
| 1870 |
-
"Chemistry": {
|
| 1871 |
-
"Average Score": 31.382959631870822,
|
| 1872 |
-
"Standard Deviation": null,
|
| 1873 |
-
"Rank": 36
|
| 1874 |
-
}
|
| 1875 |
-
}
|
| 1876 |
-
},
|
| 1877 |
-
{
|
| 1878 |
-
"config": {
|
| 1879 |
-
"model_name": "mistral-7b-instruct-1",
|
| 1880 |
-
"organization": "Mistral",
|
| 1881 |
-
"license": "Apache 2.0",
|
| 1882 |
-
"knowledge_cutoff": "2023/12"
|
| 1883 |
-
},
|
| 1884 |
-
"results": {
|
| 1885 |
-
"OVERALL": {
|
| 1886 |
-
"Average Score": 0.23016314,
|
| 1887 |
-
"Standard Deviation": 0.07137625271,
|
| 1888 |
-
"Rank": 46
|
| 1889 |
-
},
|
| 1890 |
-
"Geometry": {
|
| 1891 |
-
"Average Score": 0.161799938,
|
| 1892 |
-
"Standard Deviation": 0.03595278559,
|
| 1893 |
-
"Rank": 46
|
| 1894 |
-
},
|
| 1895 |
-
"Algebra": {
|
| 1896 |
-
"Average Score": 0.210341624,
|
| 1897 |
-
"Standard Deviation": 0.01736539119,
|
| 1898 |
-
"Rank": 43
|
| 1899 |
-
},
|
| 1900 |
-
"Probability": {
|
| 1901 |
-
"Average Score": 0.238417922,
|
| 1902 |
-
"Standard Deviation": 0.03744211933,
|
| 1903 |
-
"Rank": 42
|
| 1904 |
-
},
|
| 1905 |
-
"Logical": {
|
| 1906 |
-
"Average Score": 0.142636601,
|
| 1907 |
-
"Standard Deviation": 0.02080406365,
|
| 1908 |
-
"Rank": 46
|
| 1909 |
-
},
|
| 1910 |
-
"Social": {
|
| 1911 |
-
"Average Score": 0.117646827,
|
| 1912 |
-
"Standard Deviation": 0.009321202779,
|
| 1913 |
-
"Rank": 49
|
| 1914 |
-
},
|
| 1915 |
-
"Chemistry": {
|
| 1916 |
-
"Average Score": 18.929093202755805,
|
| 1917 |
-
"Standard Deviation": null,
|
| 1918 |
-
"Rank": 43
|
| 1919 |
-
}
|
| 1920 |
-
}
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"config": {
|
| 1924 |
-
"model_name": "vicuna-13b",
|
| 1925 |
-
"organization": "LMSYS",
|
| 1926 |
-
"license": "Non-commercial",
|
| 1927 |
-
"knowledge_cutoff": "2023/07"
|
| 1928 |
-
},
|
| 1929 |
-
"results": {
|
| 1930 |
-
"OVERALL": {
|
| 1931 |
-
"Average Score": 0.201892849,
|
| 1932 |
-
"Standard Deviation": 0.06021749802,
|
| 1933 |
-
"Rank": 47
|
| 1934 |
-
},
|
| 1935 |
-
"Geometry": {
|
| 1936 |
-
"Average Score": 0.200941928,
|
| 1937 |
-
"Standard Deviation": 0.03366817781,
|
| 1938 |
-
"Rank": 43
|
| 1939 |
-
},
|
| 1940 |
-
"Algebra": {
|
| 1941 |
-
"Average Score": 0.196123323,
|
| 1942 |
-
"Standard Deviation": 0.0135715643,
|
| 1943 |
-
"Rank": 44
|
| 1944 |
-
},
|
| 1945 |
-
"Probability": {
|
| 1946 |
-
"Average Score": 0.141214079,
|
| 1947 |
-
"Standard Deviation": 0.02721328211,
|
| 1948 |
-
"Rank": 46
|
| 1949 |
-
},
|
| 1950 |
-
"Logical": {
|
| 1951 |
-
"Average Score": 0.148598631,
|
| 1952 |
-
"Standard Deviation": 0.02241523892,
|
| 1953 |
-
"Rank": 44
|
| 1954 |
-
},
|
| 1955 |
-
"Social": {
|
| 1956 |
-
"Average Score": 0.124655135,
|
| 1957 |
-
"Standard Deviation": 0.01122382671,
|
| 1958 |
-
"Rank": 48
|
| 1959 |
-
},
|
| 1960 |
-
"Chemistry": {
|
| 1961 |
-
"Average Score": 21.840013221590294,
|
| 1962 |
-
"Standard Deviation": null,
|
| 1963 |
-
"Rank": 41
|
| 1964 |
-
}
|
| 1965 |
-
}
|
| 1966 |
-
},
|
| 1967 |
-
{
|
| 1968 |
-
"config": {
|
| 1969 |
-
"model_name": "zephyr-7b-beta",
|
| 1970 |
-
"organization": "HuggingFace",
|
| 1971 |
-
"license": "MIT",
|
| 1972 |
-
"knowledge_cutoff": "2023/10"
|
| 1973 |
-
},
|
| 1974 |
-
"results": {
|
| 1975 |
-
"OVERALL": {
|
| 1976 |
-
"Average Score": 0.102705119,
|
| 1977 |
-
"Standard Deviation": 0.03683757312,
|
| 1978 |
-
"Rank": 50
|
| 1979 |
-
},
|
| 1980 |
-
"Geometry": {
|
| 1981 |
-
"Average Score": 0.114005544,
|
| 1982 |
-
"Standard Deviation": 0.03144354365,
|
| 1983 |
-
"Rank": 47
|
| 1984 |
-
},
|
| 1985 |
-
"Algebra": {
|
| 1986 |
-
"Average Score": 0.141766633,
|
| 1987 |
-
"Standard Deviation": 0.03179520129,
|
| 1988 |
-
"Rank": 45
|
| 1989 |
-
},
|
| 1990 |
-
"Probability": {
|
| 1991 |
-
"Average Score": 0.089050714,
|
| 1992 |
-
"Standard Deviation": 0.002136754266,
|
| 1993 |
-
"Rank": 49
|
| 1994 |
-
},
|
| 1995 |
-
"Logical": {
|
| 1996 |
-
"Average Score": 0.069520789,
|
| 1997 |
-
"Standard Deviation": 0.004477840857,
|
| 1998 |
-
"Rank": 51
|
| 1999 |
-
},
|
| 2000 |
-
"Social": {
|
| 2001 |
-
"Average Score": 0.0,
|
| 2002 |
-
"Standard Deviation": 0.0,
|
| 2003 |
-
"Rank": 54
|
| 2004 |
-
},
|
| 2005 |
-
"Chemistry": {
|
| 2006 |
-
"Average Score": 18.92902220864132,
|
| 2007 |
-
"Standard Deviation": null,
|
| 2008 |
-
"Rank": 44
|
| 2009 |
-
}
|
| 2010 |
-
}
|
| 2011 |
-
},
|
| 2012 |
-
{
|
| 2013 |
-
"config": {
|
| 2014 |
-
"model_name": "gemma-1.1-2b-it",
|
| 2015 |
-
"organization": "Google",
|
| 2016 |
-
"license": "Gemma License",
|
| 2017 |
-
"knowledge_cutoff": "2024/02"
|
| 2018 |
-
},
|
| 2019 |
-
"results": {
|
| 2020 |
-
"OVERALL": {
|
| 2021 |
-
"Average Score": 0.257700845,
|
| 2022 |
-
"Standard Deviation": 0.07369021445,
|
| 2023 |
-
"Rank": 44
|
| 2024 |
-
},
|
| 2025 |
-
"Geometry": {
|
| 2026 |
-
"Average Score": 0.183974034,
|
| 2027 |
-
"Standard Deviation": 0.0215548886,
|
| 2028 |
-
"Rank": 45
|
| 2029 |
-
},
|
| 2030 |
-
"Algebra": {
|
| 2031 |
-
"Average Score": 0.13422252,
|
| 2032 |
-
"Standard Deviation": 0.01922819511,
|
| 2033 |
-
"Rank": 46
|
| 2034 |
-
},
|
| 2035 |
-
"Probability": {
|
| 2036 |
-
"Average Score": 0.095628657,
|
| 2037 |
-
"Standard Deviation": 0.007536076456,
|
| 2038 |
-
"Rank": 48
|
| 2039 |
-
},
|
| 2040 |
-
"Logical": {
|
| 2041 |
-
"Average Score": 0.094965074,
|
| 2042 |
-
"Standard Deviation": 0.005019175487,
|
| 2043 |
-
"Rank": 49
|
| 2044 |
-
},
|
| 2045 |
-
"Social": {
|
| 2046 |
-
"Average Score": 0.167796727,
|
| 2047 |
-
"Standard Deviation": 0.01666541942,
|
| 2048 |
-
"Rank": 44
|
| 2049 |
-
},
|
| 2050 |
-
"Chemistry": {
|
| 2051 |
-
"Average Score": 20.724691953843916,
|
| 2052 |
-
"Standard Deviation": null,
|
| 2053 |
-
"Rank": 42
|
| 2054 |
-
}
|
| 2055 |
-
}
|
| 2056 |
-
},
|
| 2057 |
-
{
|
| 2058 |
-
"config": {
|
| 2059 |
-
"model_name": "llama2-7b-chat",
|
| 2060 |
-
"organization": "Meta",
|
| 2061 |
-
"license": "Llama 2 Community",
|
| 2062 |
-
"knowledge_cutoff": "2023/07"
|
| 2063 |
-
},
|
| 2064 |
-
"results": {
|
| 2065 |
-
"OVERALL": {
|
| 2066 |
-
"Average Score": 0.260189428,
|
| 2067 |
-
"Standard Deviation": 0.08019299364,
|
| 2068 |
-
"Rank": 43
|
| 2069 |
-
},
|
| 2070 |
-
"Geometry": {
|
| 2071 |
-
"Average Score": 0.087067276,
|
| 2072 |
-
"Standard Deviation": 0.04274343402,
|
| 2073 |
-
"Rank": 48
|
| 2074 |
-
},
|
| 2075 |
-
"Algebra": {
|
| 2076 |
-
"Average Score": 0.12308805,
|
| 2077 |
-
"Standard Deviation": 0.01856053622,
|
| 2078 |
-
"Rank": 47
|
| 2079 |
-
},
|
| 2080 |
-
"Probability": {
|
| 2081 |
-
"Average Score": 0.087515438,
|
| 2082 |
-
"Standard Deviation": 0.006315053573,
|
| 2083 |
-
"Rank": 50
|
| 2084 |
-
},
|
| 2085 |
-
"Logical": {
|
| 2086 |
-
"Average Score": 0.17312827,
|
| 2087 |
-
"Standard Deviation": 0.01867044092,
|
| 2088 |
-
"Rank": 43
|
| 2089 |
-
},
|
| 2090 |
-
"Social": {
|
| 2091 |
-
"Average Score": 0.152905272,
|
| 2092 |
-
"Standard Deviation": 0.007166957097,
|
| 2093 |
-
"Rank": 45
|
| 2094 |
-
},
|
| 2095 |
-
"Chemistry": {
|
| 2096 |
-
"Average Score": 15.730513733660898,
|
| 2097 |
-
"Standard Deviation": null,
|
| 2098 |
-
"Rank": 46
|
| 2099 |
-
}
|
| 2100 |
-
}
|
| 2101 |
-
},
|
| 2102 |
-
{
|
| 2103 |
-
"config": {
|
| 2104 |
-
"model_name": "gemma-2b-it",
|
| 2105 |
-
"organization": "Google",
|
| 2106 |
-
"license": "Gemma License",
|
| 2107 |
-
"knowledge_cutoff": "2024/02"
|
| 2108 |
-
},
|
| 2109 |
-
"results": {
|
| 2110 |
-
"OVERALL": {
|
| 2111 |
-
"Average Score": 0.234172069,
|
| 2112 |
-
"Standard Deviation": 0.06522685718,
|
| 2113 |
-
"Rank": 45
|
| 2114 |
-
},
|
| 2115 |
-
"Geometry": {
|
| 2116 |
-
"Average Score": 0.198571153,
|
| 2117 |
-
"Standard Deviation": 0.01699161031,
|
| 2118 |
-
"Rank": 44
|
| 2119 |
-
},
|
| 2120 |
-
"Algebra": {
|
| 2121 |
-
"Average Score": 0.109883009,
|
| 2122 |
-
"Standard Deviation": 0.01520005833,
|
| 2123 |
-
"Rank": 48
|
| 2124 |
-
},
|
| 2125 |
-
"Probability": {
|
| 2126 |
-
"Average Score": 0.06467432,
|
| 2127 |
-
"Standard Deviation": 0.002117497231,
|
| 2128 |
-
"Rank": 52
|
| 2129 |
-
},
|
| 2130 |
-
"Logical": {
|
| 2131 |
-
"Average Score": 0.039624492,
|
| 2132 |
-
"Standard Deviation": 0.007606972686,
|
| 2133 |
-
"Rank": 52
|
| 2134 |
-
},
|
| 2135 |
-
"Social": {
|
| 2136 |
-
"Average Score": 0.087452913,
|
| 2137 |
-
"Standard Deviation": 0.008170146562,
|
| 2138 |
-
"Rank": 52
|
| 2139 |
-
},
|
| 2140 |
-
"Chemistry": {
|
| 2141 |
-
"Average Score": 17.2715657115764,
|
| 2142 |
-
"Standard Deviation": null,
|
| 2143 |
-
"Rank": 45
|
| 2144 |
-
}
|
| 2145 |
-
}
|
| 2146 |
-
},
|
| 2147 |
-
{
|
| 2148 |
-
"config": {
|
| 2149 |
-
"model_name": "llama2-13b-chat",
|
| 2150 |
-
"organization": "Meta",
|
| 2151 |
-
"license": "Llama 2 Community",
|
| 2152 |
-
"knowledge_cutoff": "2023/07"
|
| 2153 |
-
},
|
| 2154 |
-
"results": {
|
| 2155 |
-
"OVERALL": {
|
| 2156 |
-
"Average Score": 0.263305684,
|
| 2157 |
-
"Standard Deviation": 0.07283640689,
|
| 2158 |
-
"Rank": 42
|
| 2159 |
-
},
|
| 2160 |
-
"Geometry": {
|
| 2161 |
-
"Average Score": 0.072729954,
|
| 2162 |
-
"Standard Deviation": 0.02315988261,
|
| 2163 |
-
"Rank": 50
|
| 2164 |
-
},
|
| 2165 |
-
"Algebra": {
|
| 2166 |
-
"Average Score": 0.080371692,
|
| 2167 |
-
"Standard Deviation": 0.01277569453,
|
| 2168 |
-
"Rank": 49
|
| 2169 |
-
},
|
| 2170 |
-
"Probability": {
|
| 2171 |
-
"Average Score": 0.117757344,
|
| 2172 |
-
"Standard Deviation": 0.02418619619,
|
| 2173 |
-
"Rank": 47
|
| 2174 |
-
},
|
| 2175 |
-
"Logical": {
|
| 2176 |
-
"Average Score": 0.193149889,
|
| 2177 |
-
"Standard Deviation": 0.01776690764,
|
| 2178 |
-
"Rank": 40
|
| 2179 |
-
},
|
| 2180 |
-
"Social": {
|
| 2181 |
-
"Average Score": 0.149125922,
|
| 2182 |
-
"Standard Deviation": 0.01157416827,
|
| 2183 |
-
"Rank": 46
|
| 2184 |
-
},
|
| 2185 |
-
"Chemistry": {
|
| 2186 |
-
"Average Score": 13.17258252933903,
|
| 2187 |
-
"Standard Deviation": null,
|
| 2188 |
-
"Rank": 49
|
| 2189 |
-
}
|
| 2190 |
-
}
|
| 2191 |
-
},
|
| 2192 |
-
{
|
| 2193 |
-
"config": {
|
| 2194 |
-
"model_name": "vicuna-7b",
|
| 2195 |
-
"organization": "LMSYS",
|
| 2196 |
-
"license": "Non-commercial",
|
| 2197 |
-
"knowledge_cutoff": "2023/07"
|
| 2198 |
-
},
|
| 2199 |
-
"results": {
|
| 2200 |
-
"OVERALL": {
|
| 2201 |
-
"Average Score": 0.198839786,
|
| 2202 |
-
"Standard Deviation": 0.05725381576,
|
| 2203 |
-
"Rank": 48
|
| 2204 |
-
},
|
| 2205 |
-
"Geometry": {
|
| 2206 |
-
"Average Score": 0.083457058,
|
| 2207 |
-
"Standard Deviation": 0.02520989111,
|
| 2208 |
-
"Rank": 49
|
| 2209 |
-
},
|
| 2210 |
-
"Algebra": {
|
| 2211 |
-
"Average Score": 0.070883882,
|
| 2212 |
-
"Standard Deviation": 0.007315853253,
|
| 2213 |
-
"Rank": 50
|
| 2214 |
-
},
|
| 2215 |
-
"Probability": {
|
| 2216 |
-
"Average Score": 0.080987673,
|
| 2217 |
-
"Standard Deviation": 0.005474288861,
|
| 2218 |
-
"Rank": 51
|
| 2219 |
-
},
|
| 2220 |
-
"Logical": {
|
| 2221 |
-
"Average Score": 0.100065588,
|
| 2222 |
-
"Standard Deviation": 0.003561886452,
|
| 2223 |
-
"Rank": 48
|
| 2224 |
-
},
|
| 2225 |
-
"Social": {
|
| 2226 |
-
"Average Score": 0.111076414,
|
| 2227 |
-
"Standard Deviation": 0.004805626512,
|
| 2228 |
-
"Rank": 50
|
| 2229 |
-
},
|
| 2230 |
-
"Chemistry": {
|
| 2231 |
-
"Average Score": 14.255194156624162,
|
| 2232 |
-
"Standard Deviation": null,
|
| 2233 |
-
"Rank": 47
|
| 2234 |
-
}
|
| 2235 |
-
}
|
| 2236 |
-
},
|
| 2237 |
-
{
|
| 2238 |
-
"config": {
|
| 2239 |
-
"model_name": "koala-13b",
|
| 2240 |
-
"organization": "UC Berkeley",
|
| 2241 |
-
"license": "Non-commercial",
|
| 2242 |
-
"knowledge_cutoff": "2023/04"
|
| 2243 |
-
},
|
| 2244 |
-
"results": {
|
| 2245 |
-
"OVERALL": {
|
| 2246 |
-
"Average Score": 0.09387188,
|
| 2247 |
-
"Standard Deviation": 0.02642167489,
|
| 2248 |
-
"Rank": 51
|
| 2249 |
-
},
|
| 2250 |
-
"Geometry": {
|
| 2251 |
-
"Average Score": 0.017374001,
|
| 2252 |
-
"Standard Deviation": 0.01747053557,
|
| 2253 |
-
"Rank": 51
|
| 2254 |
-
},
|
| 2255 |
-
"Algebra": {
|
| 2256 |
-
"Average Score": 0.018129197,
|
| 2257 |
-
"Standard Deviation": 0.01054371383,
|
| 2258 |
-
"Rank": 51
|
| 2259 |
-
},
|
| 2260 |
-
"Probability": {
|
| 2261 |
-
"Average Score": 0.043654362,
|
| 2262 |
-
"Standard Deviation": 0.004288231886,
|
| 2263 |
-
"Rank": 53
|
| 2264 |
-
},
|
| 2265 |
-
"Logical": {
|
| 2266 |
-
"Average Score": 0.074694053,
|
| 2267 |
-
"Standard Deviation": 0.002674646998,
|
| 2268 |
-
"Rank": 50
|
| 2269 |
-
},
|
| 2270 |
-
"Social": {
|
| 2271 |
-
"Average Score": 0.096983835,
|
| 2272 |
-
"Standard Deviation": 0.007847059783,
|
| 2273 |
-
"Rank": 51
|
| 2274 |
-
},
|
| 2275 |
-
"Chemistry": {
|
| 2276 |
-
"Average Score": 6.36433272373514,
|
| 2277 |
-
"Standard Deviation": null,
|
| 2278 |
-
"Rank": 50
|
| 2279 |
-
}
|
| 2280 |
-
}
|
| 2281 |
-
},
|
| 2282 |
-
{
|
| 2283 |
-
"config": {
|
| 2284 |
-
"model_name": "openassistant-pythia-12b",
|
| 2285 |
-
"organization": "OpenAssistant",
|
| 2286 |
-
"license": "Non-commercial",
|
| 2287 |
-
"knowledge_cutoff": "2023/04"
|
| 2288 |
-
},
|
| 2289 |
-
"results": {
|
| 2290 |
-
"OVERALL": {
|
| 2291 |
-
"Average Score": 0.0,
|
| 2292 |
-
"Standard Deviation": 0.0,
|
| 2293 |
-
"Rank": 52
|
| 2294 |
-
},
|
| 2295 |
-
"Geometry": {
|
| 2296 |
-
"Average Score": 0.0,
|
| 2297 |
-
"Standard Deviation": 0.0,
|
| 2298 |
-
"Rank": 52
|
| 2299 |
-
},
|
| 2300 |
-
"Algebra": {
|
| 2301 |
-
"Average Score": 0.0,
|
| 2302 |
-
"Standard Deviation": 0.0,
|
| 2303 |
-
"Rank": 52
|
| 2304 |
-
},
|
| 2305 |
-
"Probability": {
|
| 2306 |
-
"Average Score": 0.0,
|
| 2307 |
-
"Standard Deviation": 0.0,
|
| 2308 |
-
"Rank": 54
|
| 2309 |
-
},
|
| 2310 |
-
"Logical": {
|
| 2311 |
-
"Average Score": 0.0,
|
| 2312 |
-
"Standard Deviation": 0.0,
|
| 2313 |
-
"Rank": 53
|
| 2314 |
-
},
|
| 2315 |
-
"Social": {
|
| 2316 |
-
"Average Score": 0.030792528,
|
| 2317 |
-
"Standard Deviation": 0.007518796391,
|
| 2318 |
-
"Rank": 53
|
| 2319 |
-
},
|
| 2320 |
-
"Chemistry": {
|
| 2321 |
-
"Average Score": 0.0,
|
| 2322 |
-
"Standard Deviation": null,
|
| 2323 |
-
"Rank": 51
|
| 2324 |
-
}
|
| 2325 |
-
}
|
| 2326 |
-
}
|
| 2327 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/models_2024-10-09-06:22:21.122422.json
DELETED
|
@@ -1,2372 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"config": {
|
| 4 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 5 |
-
"organization": "OpenAI",
|
| 6 |
-
"license": "Proprietary",
|
| 7 |
-
"knowledge_cutoff": "2023/10"
|
| 8 |
-
},
|
| 9 |
-
"results": {
|
| 10 |
-
"OVERALL": {
|
| 11 |
-
"Average Score": 0.974329609,
|
| 12 |
-
"Standard Deviation": 0.005024959031,
|
| 13 |
-
"Rank": 2
|
| 14 |
-
},
|
| 15 |
-
"Geometry": {
|
| 16 |
-
"Average Score": 0.976028578,
|
| 17 |
-
"Standard Deviation": 0.01507912373,
|
| 18 |
-
"Rank": 3
|
| 19 |
-
},
|
| 20 |
-
"Algebra": {
|
| 21 |
-
"Average Score": 0.951199453,
|
| 22 |
-
"Standard Deviation": 0.08452452108,
|
| 23 |
-
"Rank": 3
|
| 24 |
-
},
|
| 25 |
-
"Probability": {
|
| 26 |
-
"Average Score": 0.842116641,
|
| 27 |
-
"Standard Deviation": 0.006267759054,
|
| 28 |
-
"Rank": 3
|
| 29 |
-
},
|
| 30 |
-
"Logical": {
|
| 31 |
-
"Average Score": 0.828490728,
|
| 32 |
-
"Standard Deviation": 0.009134213144,
|
| 33 |
-
"Rank": 3
|
| 34 |
-
},
|
| 35 |
-
"Social": {
|
| 36 |
-
"Average Score": 0.815902987,
|
| 37 |
-
"Standard Deviation": 0.0196254222,
|
| 38 |
-
"Rank": 3
|
| 39 |
-
},
|
| 40 |
-
"Chemistry": {
|
| 41 |
-
"Average Score": 100.0,
|
| 42 |
-
"Standard Deviation": null,
|
| 43 |
-
"Rank": 1
|
| 44 |
-
}
|
| 45 |
-
}
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"config": {
|
| 49 |
-
"model_name": "meta-llama-3.1-70b-instruct",
|
| 50 |
-
"organization": "Meta",
|
| 51 |
-
"license": "Llama 3.1 Community",
|
| 52 |
-
"knowledge_cutoff": "2023/12"
|
| 53 |
-
},
|
| 54 |
-
"results": {
|
| 55 |
-
"OVERALL": {
|
| 56 |
-
"Average Score": 0.708874896,
|
| 57 |
-
"Standard Deviation": 0.1315111956,
|
| 58 |
-
"Rank": 13
|
| 59 |
-
},
|
| 60 |
-
"Geometry": {
|
| 61 |
-
"Average Score": 0.76184398,
|
| 62 |
-
"Standard Deviation": 0.01790377984,
|
| 63 |
-
"Rank": 10
|
| 64 |
-
},
|
| 65 |
-
"Algebra": {
|
| 66 |
-
"Average Score": 0.732041699,
|
| 67 |
-
"Standard Deviation": 0.02621439062,
|
| 68 |
-
"Rank": 9
|
| 69 |
-
},
|
| 70 |
-
"Probability": {
|
| 71 |
-
"Average Score": 0.676208383,
|
| 72 |
-
"Standard Deviation": 0.05131201636,
|
| 73 |
-
"Rank": 10
|
| 74 |
-
},
|
| 75 |
-
"Logical": {
|
| 76 |
-
"Average Score": 0.620018631,
|
| 77 |
-
"Standard Deviation": 0.02518873821,
|
| 78 |
-
"Rank": 14
|
| 79 |
-
},
|
| 80 |
-
"Social": {
|
| 81 |
-
"Average Score": 0.45872939,
|
| 82 |
-
"Standard Deviation": 0.05347039576,
|
| 83 |
-
"Rank": 20
|
| 84 |
-
},
|
| 85 |
-
"Chemistry": {
|
| 86 |
-
"Average Score": 84.36815192532764,
|
| 87 |
-
"Standard Deviation": null,
|
| 88 |
-
"Rank": 4
|
| 89 |
-
}
|
| 90 |
-
}
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"config": {
|
| 94 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 95 |
-
"organization": "OpenAI",
|
| 96 |
-
"license": "Proprietary",
|
| 97 |
-
"knowledge_cutoff": "2023/10"
|
| 98 |
-
},
|
| 99 |
-
"results": {
|
| 100 |
-
"OVERALL": {
|
| 101 |
-
"Average Score": 0.846571548,
|
| 102 |
-
"Standard Deviation": 0.03394056554,
|
| 103 |
-
"Rank": 6
|
| 104 |
-
},
|
| 105 |
-
"Geometry": {
|
| 106 |
-
"Average Score": 0.99773096,
|
| 107 |
-
"Standard Deviation": 0.002835555172,
|
| 108 |
-
"Rank": 1
|
| 109 |
-
},
|
| 110 |
-
"Algebra": {
|
| 111 |
-
"Average Score": 1.0,
|
| 112 |
-
"Standard Deviation": 0.0,
|
| 113 |
-
"Rank": 1
|
| 114 |
-
},
|
| 115 |
-
"Probability": {
|
| 116 |
-
"Average Score": 0.78855795,
|
| 117 |
-
"Standard Deviation": 0.008188675452,
|
| 118 |
-
"Rank": 6
|
| 119 |
-
},
|
| 120 |
-
"Logical": {
|
| 121 |
-
"Average Score": 0.668635768,
|
| 122 |
-
"Standard Deviation": 0.03466314094,
|
| 123 |
-
"Rank": 11
|
| 124 |
-
},
|
| 125 |
-
"Social": {
|
| 126 |
-
"Average Score": 0.680417314,
|
| 127 |
-
"Standard Deviation": 0.00656867063,
|
| 128 |
-
"Rank": 8
|
| 129 |
-
},
|
| 130 |
-
"Chemistry": {
|
| 131 |
-
"Average Score": 92.43090226400756,
|
| 132 |
-
"Standard Deviation": null,
|
| 133 |
-
"Rank": 2
|
| 134 |
-
}
|
| 135 |
-
}
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"config": {
|
| 139 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 140 |
-
"organization": "OpenAI",
|
| 141 |
-
"license": "Proprietary",
|
| 142 |
-
"knowledge_cutoff": "2023/10"
|
| 143 |
-
},
|
| 144 |
-
"results": {
|
| 145 |
-
"OVERALL": {
|
| 146 |
-
"Average Score": 0.846334477,
|
| 147 |
-
"Standard Deviation": 0.09377911572,
|
| 148 |
-
"Rank": 7
|
| 149 |
-
},
|
| 150 |
-
"Geometry": {
|
| 151 |
-
"Average Score": 0.972472377,
|
| 152 |
-
"Standard Deviation": 0.01648274205,
|
| 153 |
-
"Rank": 4
|
| 154 |
-
},
|
| 155 |
-
"Algebra": {
|
| 156 |
-
"Average Score": 0.995511298,
|
| 157 |
-
"Standard Deviation": 0.004097802515,
|
| 158 |
-
"Rank": 2
|
| 159 |
-
},
|
| 160 |
-
"Probability": {
|
| 161 |
-
"Average Score": 0.812149974,
|
| 162 |
-
"Standard Deviation": 0.007669585485,
|
| 163 |
-
"Rank": 4
|
| 164 |
-
},
|
| 165 |
-
"Logical": {
|
| 166 |
-
"Average Score": 0.755019692,
|
| 167 |
-
"Standard Deviation": 0.008149588572,
|
| 168 |
-
"Rank": 6
|
| 169 |
-
},
|
| 170 |
-
"Social": {
|
| 171 |
-
"Average Score": 0.609875087,
|
| 172 |
-
"Standard Deviation": 0.038729239,
|
| 173 |
-
"Rank": 13
|
| 174 |
-
},
|
| 175 |
-
"Chemistry": {
|
| 176 |
-
"Average Score": 79.1592634699295,
|
| 177 |
-
"Standard Deviation": null,
|
| 178 |
-
"Rank": 6
|
| 179 |
-
}
|
| 180 |
-
}
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"config": {
|
| 184 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 185 |
-
"organization": "OpenAI",
|
| 186 |
-
"license": "Proprietary",
|
| 187 |
-
"knowledge_cutoff": "2023/12"
|
| 188 |
-
},
|
| 189 |
-
"results": {
|
| 190 |
-
"OVERALL": {
|
| 191 |
-
"Average Score": 0.855357972,
|
| 192 |
-
"Standard Deviation": 0.1016986368,
|
| 193 |
-
"Rank": 4
|
| 194 |
-
},
|
| 195 |
-
"Geometry": {
|
| 196 |
-
"Average Score": 0.95374588,
|
| 197 |
-
"Standard Deviation": 0.03109307166,
|
| 198 |
-
"Rank": 5
|
| 199 |
-
},
|
| 200 |
-
"Algebra": {
|
| 201 |
-
"Average Score": 0.930945223,
|
| 202 |
-
"Standard Deviation": 0.06705136813,
|
| 203 |
-
"Rank": 4
|
| 204 |
-
},
|
| 205 |
-
"Probability": {
|
| 206 |
-
"Average Score": 0.750705448,
|
| 207 |
-
"Standard Deviation": 0.05944483103,
|
| 208 |
-
"Rank": 8
|
| 209 |
-
},
|
| 210 |
-
"Logical": {
|
| 211 |
-
"Average Score": 0.77906699,
|
| 212 |
-
"Standard Deviation": 0.007406734161,
|
| 213 |
-
"Rank": 4
|
| 214 |
-
},
|
| 215 |
-
"Social": {
|
| 216 |
-
"Average Score": 0.715935163,
|
| 217 |
-
"Standard Deviation": 0.1209141409,
|
| 218 |
-
"Rank": 6
|
| 219 |
-
},
|
| 220 |
-
"Chemistry": {
|
| 221 |
-
"Average Score": 70.73143363230263,
|
| 222 |
-
"Standard Deviation": null,
|
| 223 |
-
"Rank": 11
|
| 224 |
-
}
|
| 225 |
-
}
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"config": {
|
| 229 |
-
"model_name": "gemini-1.5-pro-001",
|
| 230 |
-
"organization": "Google",
|
| 231 |
-
"license": "Proprietary",
|
| 232 |
-
"knowledge_cutoff": "2023/11"
|
| 233 |
-
},
|
| 234 |
-
"results": {
|
| 235 |
-
"OVERALL": {
|
| 236 |
-
"Average Score": 0.797187842,
|
| 237 |
-
"Standard Deviation": 0.0272375249,
|
| 238 |
-
"Rank": 10
|
| 239 |
-
},
|
| 240 |
-
"Geometry": {
|
| 241 |
-
"Average Score": 0.9947169,
|
| 242 |
-
"Standard Deviation": 0.009150597621,
|
| 243 |
-
"Rank": 2
|
| 244 |
-
},
|
| 245 |
-
"Algebra": {
|
| 246 |
-
"Average Score": 0.857464301,
|
| 247 |
-
"Standard Deviation": 0.05014285338,
|
| 248 |
-
"Rank": 5
|
| 249 |
-
},
|
| 250 |
-
"Probability": {
|
| 251 |
-
"Average Score": 0.651781767,
|
| 252 |
-
"Standard Deviation": 0.04156998547,
|
| 253 |
-
"Rank": 11
|
| 254 |
-
},
|
| 255 |
-
"Logical": {
|
| 256 |
-
"Average Score": 0.739745471,
|
| 257 |
-
"Standard Deviation": 0.01631532019,
|
| 258 |
-
"Rank": 7
|
| 259 |
-
},
|
| 260 |
-
"Social": {
|
| 261 |
-
"Average Score": 0.649601885,
|
| 262 |
-
"Standard Deviation": 0.104854889,
|
| 263 |
-
"Rank": 11
|
| 264 |
-
}
|
| 265 |
-
}
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"config": {
|
| 269 |
-
"model_name": "qwen2-72b-instruct",
|
| 270 |
-
"organization": "Alibaba",
|
| 271 |
-
"license": "Qianwen LICENSE",
|
| 272 |
-
"knowledge_cutoff": "2024/09"
|
| 273 |
-
},
|
| 274 |
-
"results": {
|
| 275 |
-
"OVERALL": {
|
| 276 |
-
"Average Score": 0.737918558,
|
| 277 |
-
"Standard Deviation": 0.09069077339,
|
| 278 |
-
"Rank": 11
|
| 279 |
-
},
|
| 280 |
-
"Geometry": {
|
| 281 |
-
"Average Score": 0.796870305,
|
| 282 |
-
"Standard Deviation": 0.0509025346,
|
| 283 |
-
"Rank": 9
|
| 284 |
-
},
|
| 285 |
-
"Algebra": {
|
| 286 |
-
"Average Score": 0.836194231,
|
| 287 |
-
"Standard Deviation": 0.04517093028,
|
| 288 |
-
"Rank": 6
|
| 289 |
-
},
|
| 290 |
-
"Probability": {
|
| 291 |
-
"Average Score": 0.788068004,
|
| 292 |
-
"Standard Deviation": 0.007288989044,
|
| 293 |
-
"Rank": 7
|
| 294 |
-
},
|
| 295 |
-
"Logical": {
|
| 296 |
-
"Average Score": 0.619300904,
|
| 297 |
-
"Standard Deviation": 0.06377931612,
|
| 298 |
-
"Rank": 15
|
| 299 |
-
},
|
| 300 |
-
"Social": {
|
| 301 |
-
"Average Score": 0.652578786,
|
| 302 |
-
"Standard Deviation": 0.04259293171,
|
| 303 |
-
"Rank": 10
|
| 304 |
-
},
|
| 305 |
-
"Chemistry": {
|
| 306 |
-
"Average Score": 73.54037778797029,
|
| 307 |
-
"Standard Deviation": null,
|
| 308 |
-
"Rank": 8
|
| 309 |
-
}
|
| 310 |
-
}
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"config": {
|
| 314 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 315 |
-
"organization": "OpenAI",
|
| 316 |
-
"license": "Proprietary",
|
| 317 |
-
"knowledge_cutoff": "2023/10"
|
| 318 |
-
},
|
| 319 |
-
"results": {
|
| 320 |
-
"OVERALL": {
|
| 321 |
-
"Average Score": 0.847694133,
|
| 322 |
-
"Standard Deviation": 0.02164304402,
|
| 323 |
-
"Rank": 5
|
| 324 |
-
},
|
| 325 |
-
"Geometry": {
|
| 326 |
-
"Average Score": 0.946650435,
|
| 327 |
-
"Standard Deviation": 0.01831236482,
|
| 328 |
-
"Rank": 7
|
| 329 |
-
},
|
| 330 |
-
"Algebra": {
|
| 331 |
-
"Average Score": 0.796243022,
|
| 332 |
-
"Standard Deviation": 0.05537539202,
|
| 333 |
-
"Rank": 7
|
| 334 |
-
},
|
| 335 |
-
"Probability": {
|
| 336 |
-
"Average Score": 0.798402685,
|
| 337 |
-
"Standard Deviation": 0.009404491967,
|
| 338 |
-
"Rank": 5
|
| 339 |
-
},
|
| 340 |
-
"Logical": {
|
| 341 |
-
"Average Score": 0.727009735,
|
| 342 |
-
"Standard Deviation": 0.02628110141,
|
| 343 |
-
"Rank": 8
|
| 344 |
-
},
|
| 345 |
-
"Social": {
|
| 346 |
-
"Average Score": 0.691949855,
|
| 347 |
-
"Standard Deviation": 0.02072934333,
|
| 348 |
-
"Rank": 7
|
| 349 |
-
},
|
| 350 |
-
"Chemistry": {
|
| 351 |
-
"Average Score": 88.3877070580296,
|
| 352 |
-
"Standard Deviation": null,
|
| 353 |
-
"Rank": 3
|
| 354 |
-
}
|
| 355 |
-
}
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"config": {
|
| 359 |
-
"model_name": "claude-3.5-sonnet",
|
| 360 |
-
"organization": "Anthropic",
|
| 361 |
-
"license": "Proprietary",
|
| 362 |
-
"knowledge_cutoff": "2024/04"
|
| 363 |
-
},
|
| 364 |
-
"results": {
|
| 365 |
-
"OVERALL": {
|
| 366 |
-
"Average Score": 0.839004422,
|
| 367 |
-
"Standard Deviation": 0.1461079564,
|
| 368 |
-
"Rank": 8
|
| 369 |
-
},
|
| 370 |
-
"Geometry": {
|
| 371 |
-
"Average Score": 0.95316419,
|
| 372 |
-
"Standard Deviation": 0.02081192856,
|
| 373 |
-
"Rank": 6
|
| 374 |
-
},
|
| 375 |
-
"Algebra": {
|
| 376 |
-
"Average Score": 0.759789952,
|
| 377 |
-
"Standard Deviation": 0.02611765096,
|
| 378 |
-
"Rank": 8
|
| 379 |
-
},
|
| 380 |
-
"Probability": {
|
| 381 |
-
"Average Score": 0.707730127,
|
| 382 |
-
"Standard Deviation": 0.0394436664,
|
| 383 |
-
"Rank": 9
|
| 384 |
-
},
|
| 385 |
-
"Logical": {
|
| 386 |
-
"Average Score": 0.77342666,
|
| 387 |
-
"Standard Deviation": 0.002892426458,
|
| 388 |
-
"Rank": 5
|
| 389 |
-
},
|
| 390 |
-
"Social": {
|
| 391 |
-
"Average Score": 0.790002247,
|
| 392 |
-
"Standard Deviation": 0.1007410022,
|
| 393 |
-
"Rank": 4
|
| 394 |
-
},
|
| 395 |
-
"Chemistry": {
|
| 396 |
-
"Average Score": 82.37734076815008,
|
| 397 |
-
"Standard Deviation": null,
|
| 398 |
-
"Rank": 5
|
| 399 |
-
}
|
| 400 |
-
}
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"config": {
|
| 404 |
-
"model_name": "o1-mini",
|
| 405 |
-
"organization": "OpenAI",
|
| 406 |
-
"license": "Proprietary",
|
| 407 |
-
"knowledge_cutoff": "2023/10"
|
| 408 |
-
},
|
| 409 |
-
"results": {
|
| 410 |
-
"OVERALL": {
|
| 411 |
-
"Average Score": 1.0,
|
| 412 |
-
"Standard Deviation": 0.0,
|
| 413 |
-
"Rank": 1
|
| 414 |
-
},
|
| 415 |
-
"Geometry": {
|
| 416 |
-
"Average Score": "N/A",
|
| 417 |
-
"Standard Deviation": "N/A",
|
| 418 |
-
"Rank": "N/A"
|
| 419 |
-
},
|
| 420 |
-
"Algebra": {
|
| 421 |
-
"Average Score": "N/A",
|
| 422 |
-
"Standard Deviation": "N/A",
|
| 423 |
-
"Rank": "N/A"
|
| 424 |
-
},
|
| 425 |
-
"Probability": {
|
| 426 |
-
"Average Score": 1.0,
|
| 427 |
-
"Standard Deviation": 0.0,
|
| 428 |
-
"Rank": 1
|
| 429 |
-
},
|
| 430 |
-
"Logical": {
|
| 431 |
-
"Average Score": 1.0,
|
| 432 |
-
"Standard Deviation": 0.0,
|
| 433 |
-
"Rank": 1
|
| 434 |
-
},
|
| 435 |
-
"Social": {
|
| 436 |
-
"Average Score": 0.993974241,
|
| 437 |
-
"Standard Deviation": 0.001996882328,
|
| 438 |
-
"Rank": 2
|
| 439 |
-
}
|
| 440 |
-
}
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"config": {
|
| 444 |
-
"model_name": "o1-preview",
|
| 445 |
-
"organization": "OpenAI",
|
| 446 |
-
"license": "Proprietary",
|
| 447 |
-
"knowledge_cutoff": "2023/10"
|
| 448 |
-
},
|
| 449 |
-
"results": {
|
| 450 |
-
"OVERALL": {
|
| 451 |
-
"Average Score": 0.945884589,
|
| 452 |
-
"Standard Deviation": 0.01059250762,
|
| 453 |
-
"Rank": 3
|
| 454 |
-
},
|
| 455 |
-
"Geometry": {
|
| 456 |
-
"Average Score": "N/A",
|
| 457 |
-
"Standard Deviation": "N/A",
|
| 458 |
-
"Rank": "N/A"
|
| 459 |
-
},
|
| 460 |
-
"Algebra": {
|
| 461 |
-
"Average Score": "N/A",
|
| 462 |
-
"Standard Deviation": "N/A",
|
| 463 |
-
"Rank": "N/A"
|
| 464 |
-
},
|
| 465 |
-
"Probability": {
|
| 466 |
-
"Average Score": 0.964666392,
|
| 467 |
-
"Standard Deviation": 0.003139983398,
|
| 468 |
-
"Rank": 2
|
| 469 |
-
},
|
| 470 |
-
"Logical": {
|
| 471 |
-
"Average Score": 0.987950057,
|
| 472 |
-
"Standard Deviation": 0.004881220327,
|
| 473 |
-
"Rank": 2
|
| 474 |
-
},
|
| 475 |
-
"Social": {
|
| 476 |
-
"Average Score": 1.0,
|
| 477 |
-
"Standard Deviation": 0.0,
|
| 478 |
-
"Rank": 1
|
| 479 |
-
}
|
| 480 |
-
}
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"config": {
|
| 484 |
-
"model_name": "gemini-1.5-flash-001",
|
| 485 |
-
"organization": "Google",
|
| 486 |
-
"license": "Proprietary",
|
| 487 |
-
"knowledge_cutoff": "2023/11"
|
| 488 |
-
},
|
| 489 |
-
"results": {
|
| 490 |
-
"OVERALL": {
|
| 491 |
-
"Average Score": 0.726493401,
|
| 492 |
-
"Standard Deviation": 0.01113913725,
|
| 493 |
-
"Rank": 12
|
| 494 |
-
},
|
| 495 |
-
"Geometry": {
|
| 496 |
-
"Average Score": 0.804144103,
|
| 497 |
-
"Standard Deviation": 0.1327142178,
|
| 498 |
-
"Rank": 8
|
| 499 |
-
},
|
| 500 |
-
"Algebra": {
|
| 501 |
-
"Average Score": 0.731776765,
|
| 502 |
-
"Standard Deviation": 0.02594657111,
|
| 503 |
-
"Rank": 10
|
| 504 |
-
},
|
| 505 |
-
"Probability": {
|
| 506 |
-
"Average Score": 0.614461891,
|
| 507 |
-
"Standard Deviation": 0.04690131826,
|
| 508 |
-
"Rank": 14
|
| 509 |
-
},
|
| 510 |
-
"Logical": {
|
| 511 |
-
"Average Score": 0.630805991,
|
| 512 |
-
"Standard Deviation": 0.04871350612,
|
| 513 |
-
"Rank": 13
|
| 514 |
-
},
|
| 515 |
-
"Social": {
|
| 516 |
-
"Average Score": 0.555933822,
|
| 517 |
-
"Standard Deviation": 0.1029934524,
|
| 518 |
-
"Rank": 15
|
| 519 |
-
},
|
| 520 |
-
"Chemistry": {
|
| 521 |
-
"Average Score": 72.1127762005651,
|
| 522 |
-
"Standard Deviation": null,
|
| 523 |
-
"Rank": 10
|
| 524 |
-
}
|
| 525 |
-
}
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"config": {
|
| 529 |
-
"model_name": "gpt4-1106",
|
| 530 |
-
"organization": "OpenAI",
|
| 531 |
-
"license": "Proprietary",
|
| 532 |
-
"knowledge_cutoff": "2024/04"
|
| 533 |
-
},
|
| 534 |
-
"results": {
|
| 535 |
-
"OVERALL": {
|
| 536 |
-
"Average Score": 0.816347784,
|
| 537 |
-
"Standard Deviation": 0.1566815755,
|
| 538 |
-
"Rank": 9
|
| 539 |
-
},
|
| 540 |
-
"Geometry": {
|
| 541 |
-
"Average Score": 0.71843088,
|
| 542 |
-
"Standard Deviation": 0.04778038294,
|
| 543 |
-
"Rank": 12
|
| 544 |
-
},
|
| 545 |
-
"Algebra": {
|
| 546 |
-
"Average Score": 0.712910417,
|
| 547 |
-
"Standard Deviation": 0.02581828898,
|
| 548 |
-
"Rank": 11
|
| 549 |
-
},
|
| 550 |
-
"Probability": {
|
| 551 |
-
"Average Score": 0.623947619,
|
| 552 |
-
"Standard Deviation": 0.03502982933,
|
| 553 |
-
"Rank": 13
|
| 554 |
-
},
|
| 555 |
-
"Logical": {
|
| 556 |
-
"Average Score": 0.637482274,
|
| 557 |
-
"Standard Deviation": 0.04158809888,
|
| 558 |
-
"Rank": 12
|
| 559 |
-
},
|
| 560 |
-
"Social": {
|
| 561 |
-
"Average Score": 0.450609816,
|
| 562 |
-
"Standard Deviation": 0.05208655446,
|
| 563 |
-
"Rank": 22
|
| 564 |
-
},
|
| 565 |
-
"Chemistry": {
|
| 566 |
-
"Average Score": 69.11824072252848,
|
| 567 |
-
"Standard Deviation": null,
|
| 568 |
-
"Rank": 12
|
| 569 |
-
}
|
| 570 |
-
}
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"config": {
|
| 574 |
-
"model_name": "gemma-2-27b-it",
|
| 575 |
-
"organization": "Google",
|
| 576 |
-
"license": "Gemma License",
|
| 577 |
-
"knowledge_cutoff": "2024/06"
|
| 578 |
-
},
|
| 579 |
-
"results": {
|
| 580 |
-
"OVERALL": {
|
| 581 |
-
"Average Score": 0.624169623,
|
| 582 |
-
"Standard Deviation": 0.1048365121,
|
| 583 |
-
"Rank": 15
|
| 584 |
-
},
|
| 585 |
-
"Geometry": {
|
| 586 |
-
"Average Score": 0.60112744,
|
| 587 |
-
"Standard Deviation": 0.0469109952,
|
| 588 |
-
"Rank": 18
|
| 589 |
-
},
|
| 590 |
-
"Algebra": {
|
| 591 |
-
"Average Score": 0.687955914,
|
| 592 |
-
"Standard Deviation": 0.01959958192,
|
| 593 |
-
"Rank": 12
|
| 594 |
-
},
|
| 595 |
-
"Probability": {
|
| 596 |
-
"Average Score": 0.589524771,
|
| 597 |
-
"Standard Deviation": 0.03112689325,
|
| 598 |
-
"Rank": 15
|
| 599 |
-
},
|
| 600 |
-
"Logical": {
|
| 601 |
-
"Average Score": 0.614978944,
|
| 602 |
-
"Standard Deviation": 0.05710657859,
|
| 603 |
-
"Rank": 16
|
| 604 |
-
},
|
| 605 |
-
"Social": {
|
| 606 |
-
"Average Score": 0.487844257,
|
| 607 |
-
"Standard Deviation": 0.05857760809,
|
| 608 |
-
"Rank": 18
|
| 609 |
-
},
|
| 610 |
-
"Chemistry": {
|
| 611 |
-
"Average Score": 63.28920072143611,
|
| 612 |
-
"Standard Deviation": null,
|
| 613 |
-
"Rank": 14
|
| 614 |
-
}
|
| 615 |
-
}
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"config": {
|
| 619 |
-
"model_name": "claude-3-opus",
|
| 620 |
-
"organization": "Anthropic",
|
| 621 |
-
"license": "Proprietary",
|
| 622 |
-
"knowledge_cutoff": "2023/08"
|
| 623 |
-
},
|
| 624 |
-
"results": {
|
| 625 |
-
"OVERALL": {
|
| 626 |
-
"Average Score": 0.650636271,
|
| 627 |
-
"Standard Deviation": 0.1197773541,
|
| 628 |
-
"Rank": 14
|
| 629 |
-
},
|
| 630 |
-
"Geometry": {
|
| 631 |
-
"Average Score": 0.7215743,
|
| 632 |
-
"Standard Deviation": 0.04712598358,
|
| 633 |
-
"Rank": 11
|
| 634 |
-
},
|
| 635 |
-
"Algebra": {
|
| 636 |
-
"Average Score": 0.68777327,
|
| 637 |
-
"Standard Deviation": 0.02382683713,
|
| 638 |
-
"Rank": 13
|
| 639 |
-
},
|
| 640 |
-
"Probability": {
|
| 641 |
-
"Average Score": 0.626471421,
|
| 642 |
-
"Standard Deviation": 0.02911817976,
|
| 643 |
-
"Rank": 12
|
| 644 |
-
},
|
| 645 |
-
"Logical": {
|
| 646 |
-
"Average Score": 0.692346381,
|
| 647 |
-
"Standard Deviation": 0.03617185198,
|
| 648 |
-
"Rank": 10
|
| 649 |
-
},
|
| 650 |
-
"Social": {
|
| 651 |
-
"Average Score": 0.663410854,
|
| 652 |
-
"Standard Deviation": 0.09540220876,
|
| 653 |
-
"Rank": 9
|
| 654 |
-
},
|
| 655 |
-
"Chemistry": {
|
| 656 |
-
"Average Score": 73.5404403567132,
|
| 657 |
-
"Standard Deviation": null,
|
| 658 |
-
"Rank": 7
|
| 659 |
-
}
|
| 660 |
-
}
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"config": {
|
| 664 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 665 |
-
"organization": "Google",
|
| 666 |
-
"license": "Gemma License",
|
| 667 |
-
"knowledge_cutoff": "2024/07"
|
| 668 |
-
},
|
| 669 |
-
"results": {
|
| 670 |
-
"OVERALL": {
|
| 671 |
-
"Average Score": "N/A",
|
| 672 |
-
"Standard Deviation": "N/A",
|
| 673 |
-
"Rank": "N/A"
|
| 674 |
-
},
|
| 675 |
-
"Geometry": {
|
| 676 |
-
"Average Score": 0.582787508,
|
| 677 |
-
"Standard Deviation": 0.03965204074,
|
| 678 |
-
"Rank": 19
|
| 679 |
-
},
|
| 680 |
-
"Algebra": {
|
| 681 |
-
"Average Score": 0.658648133,
|
| 682 |
-
"Standard Deviation": 0.02565919856,
|
| 683 |
-
"Rank": 14
|
| 684 |
-
},
|
| 685 |
-
"Probability": {
|
| 686 |
-
"Average Score": 0.547861265,
|
| 687 |
-
"Standard Deviation": 0.02885209131,
|
| 688 |
-
"Rank": 18
|
| 689 |
-
},
|
| 690 |
-
"Logical": {
|
| 691 |
-
"Average Score": 0.540720893,
|
| 692 |
-
"Standard Deviation": 0.01970134508,
|
| 693 |
-
"Rank": 20
|
| 694 |
-
},
|
| 695 |
-
"Social": {
|
| 696 |
-
"Average Score": 0.635266187,
|
| 697 |
-
"Standard Deviation": 0.03620021751,
|
| 698 |
-
"Rank": 12
|
| 699 |
-
},
|
| 700 |
-
"Chemistry": {
|
| 701 |
-
"Average Score": 73.43757596214863,
|
| 702 |
-
"Standard Deviation": null,
|
| 703 |
-
"Rank": 9
|
| 704 |
-
}
|
| 705 |
-
}
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"config": {
|
| 709 |
-
"model_name": "qwen1.5-72b-chat",
|
| 710 |
-
"organization": "Alibaba",
|
| 711 |
-
"license": "Qianwen LICENSE",
|
| 712 |
-
"knowledge_cutoff": "2024/03"
|
| 713 |
-
},
|
| 714 |
-
"results": {
|
| 715 |
-
"OVERALL": {
|
| 716 |
-
"Average Score": 0.519549796,
|
| 717 |
-
"Standard Deviation": 0.00903634343,
|
| 718 |
-
"Rank": 18
|
| 719 |
-
},
|
| 720 |
-
"Geometry": {
|
| 721 |
-
"Average Score": 0.543139301,
|
| 722 |
-
"Standard Deviation": 0.03425202326,
|
| 723 |
-
"Rank": 23
|
| 724 |
-
},
|
| 725 |
-
"Algebra": {
|
| 726 |
-
"Average Score": 0.635228729,
|
| 727 |
-
"Standard Deviation": 0.01944043425,
|
| 728 |
-
"Rank": 15
|
| 729 |
-
},
|
| 730 |
-
"Probability": {
|
| 731 |
-
"Average Score": 0.486948658,
|
| 732 |
-
"Standard Deviation": 0.06064655315,
|
| 733 |
-
"Rank": 22
|
| 734 |
-
},
|
| 735 |
-
"Logical": {
|
| 736 |
-
"Average Score": 0.284069394,
|
| 737 |
-
"Standard Deviation": 0.02686608506,
|
| 738 |
-
"Rank": 33
|
| 739 |
-
},
|
| 740 |
-
"Social": {
|
| 741 |
-
"Average Score": 0.415007627,
|
| 742 |
-
"Standard Deviation": 0.03920053159,
|
| 743 |
-
"Rank": 23
|
| 744 |
-
},
|
| 745 |
-
"Chemistry": {
|
| 746 |
-
"Average Score": 48.69302376665551,
|
| 747 |
-
"Standard Deviation": null,
|
| 748 |
-
"Rank": 20
|
| 749 |
-
}
|
| 750 |
-
}
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"config": {
|
| 754 |
-
"model_name": "qwen1.5-32b-chat",
|
| 755 |
-
"organization": "Alibaba",
|
| 756 |
-
"license": "Qianwen LICENSE",
|
| 757 |
-
"knowledge_cutoff": "2024/03"
|
| 758 |
-
},
|
| 759 |
-
"results": {
|
| 760 |
-
"OVERALL": {
|
| 761 |
-
"Average Score": 0.393789407,
|
| 762 |
-
"Standard Deviation": 0.05413770095,
|
| 763 |
-
"Rank": 29
|
| 764 |
-
},
|
| 765 |
-
"Geometry": {
|
| 766 |
-
"Average Score": 0.51086835,
|
| 767 |
-
"Standard Deviation": 0.04052471998,
|
| 768 |
-
"Rank": 26
|
| 769 |
-
},
|
| 770 |
-
"Algebra": {
|
| 771 |
-
"Average Score": 0.609003168,
|
| 772 |
-
"Standard Deviation": 0.04874143541,
|
| 773 |
-
"Rank": 16
|
| 774 |
-
},
|
| 775 |
-
"Probability": {
|
| 776 |
-
"Average Score": 0.476300002,
|
| 777 |
-
"Standard Deviation": 0.05322403912,
|
| 778 |
-
"Rank": 23
|
| 779 |
-
},
|
| 780 |
-
"Logical": {
|
| 781 |
-
"Average Score": 0.331781014,
|
| 782 |
-
"Standard Deviation": 0.004938997686,
|
| 783 |
-
"Rank": 30
|
| 784 |
-
},
|
| 785 |
-
"Social": {
|
| 786 |
-
"Average Score": 0.380987334,
|
| 787 |
-
"Standard Deviation": 0.03762251776,
|
| 788 |
-
"Rank": 25
|
| 789 |
-
},
|
| 790 |
-
"Chemistry": {
|
| 791 |
-
"Average Score": 45.14284028264288,
|
| 792 |
-
"Standard Deviation": null,
|
| 793 |
-
"Rank": 24
|
| 794 |
-
}
|
| 795 |
-
}
|
| 796 |
-
},
|
| 797 |
-
{
|
| 798 |
-
"config": {
|
| 799 |
-
"model_name": "google-gemma-2-9b-it",
|
| 800 |
-
"organization": "Google",
|
| 801 |
-
"license": "Proprietary",
|
| 802 |
-
"knowledge_cutoff": "2024/06"
|
| 803 |
-
},
|
| 804 |
-
"results": {
|
| 805 |
-
"OVERALL": {
|
| 806 |
-
"Average Score": 0.489663449,
|
| 807 |
-
"Standard Deviation": 0.002595702019,
|
| 808 |
-
"Rank": 21
|
| 809 |
-
},
|
| 810 |
-
"Geometry": {
|
| 811 |
-
"Average Score": 0.575371308,
|
| 812 |
-
"Standard Deviation": 0.03556220251,
|
| 813 |
-
"Rank": 21
|
| 814 |
-
},
|
| 815 |
-
"Algebra": {
|
| 816 |
-
"Average Score": 0.597045661,
|
| 817 |
-
"Standard Deviation": 0.0313828123,
|
| 818 |
-
"Rank": 17
|
| 819 |
-
},
|
| 820 |
-
"Probability": {
|
| 821 |
-
"Average Score": 0.589221807,
|
| 822 |
-
"Standard Deviation": 0.03110811656,
|
| 823 |
-
"Rank": 17
|
| 824 |
-
},
|
| 825 |
-
"Logical": {
|
| 826 |
-
"Average Score": 0.587579897,
|
| 827 |
-
"Standard Deviation": 0.05512716783,
|
| 828 |
-
"Rank": 18
|
| 829 |
-
},
|
| 830 |
-
"Social": {
|
| 831 |
-
"Average Score": 0.768337958,
|
| 832 |
-
"Standard Deviation": 0.04078610476,
|
| 833 |
-
"Rank": 5
|
| 834 |
-
},
|
| 835 |
-
"Chemistry": {
|
| 836 |
-
"Average Score": 54.03167523687635,
|
| 837 |
-
"Standard Deviation": null,
|
| 838 |
-
"Rank": 17
|
| 839 |
-
}
|
| 840 |
-
}
|
| 841 |
-
},
|
| 842 |
-
{
|
| 843 |
-
"config": {
|
| 844 |
-
"model_name": "yi-1.5-34b-chat",
|
| 845 |
-
"organization": "01 AI",
|
| 846 |
-
"license": "Proprietary",
|
| 847 |
-
"knowledge_cutoff": "2024/05"
|
| 848 |
-
},
|
| 849 |
-
"results": {
|
| 850 |
-
"OVERALL": {
|
| 851 |
-
"Average Score": 0.607812897,
|
| 852 |
-
"Standard Deviation": 0.1440881293,
|
| 853 |
-
"Rank": 16
|
| 854 |
-
},
|
| 855 |
-
"Geometry": {
|
| 856 |
-
"Average Score": 0.566666724,
|
| 857 |
-
"Standard Deviation": 0.04001381658,
|
| 858 |
-
"Rank": 22
|
| 859 |
-
},
|
| 860 |
-
"Algebra": {
|
| 861 |
-
"Average Score": 0.590997292,
|
| 862 |
-
"Standard Deviation": 0.03594087315,
|
| 863 |
-
"Rank": 18
|
| 864 |
-
},
|
| 865 |
-
"Probability": {
|
| 866 |
-
"Average Score": 0.589524589,
|
| 867 |
-
"Standard Deviation": 0.03112618772,
|
| 868 |
-
"Rank": 16
|
| 869 |
-
},
|
| 870 |
-
"Logical": {
|
| 871 |
-
"Average Score": 0.574105508,
|
| 872 |
-
"Standard Deviation": 0.03441737941,
|
| 873 |
-
"Rank": 19
|
| 874 |
-
},
|
| 875 |
-
"Social": {
|
| 876 |
-
"Average Score": 0.516980832,
|
| 877 |
-
"Standard Deviation": 0.03369347985,
|
| 878 |
-
"Rank": 17
|
| 879 |
-
},
|
| 880 |
-
"Chemistry": {
|
| 881 |
-
"Average Score": 52.148798061768964,
|
| 882 |
-
"Standard Deviation": null,
|
| 883 |
-
"Rank": 18
|
| 884 |
-
}
|
| 885 |
-
}
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"config": {
|
| 889 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 890 |
-
"organization": "Meta",
|
| 891 |
-
"license": "Llama 3.1 Community",
|
| 892 |
-
"knowledge_cutoff": "2023/12"
|
| 893 |
-
},
|
| 894 |
-
"results": {
|
| 895 |
-
"OVERALL": {
|
| 896 |
-
"Average Score": 0.505936324,
|
| 897 |
-
"Standard Deviation": 0.05286756493,
|
| 898 |
-
"Rank": 19
|
| 899 |
-
},
|
| 900 |
-
"Geometry": {
|
| 901 |
-
"Average Score": 0.522442162,
|
| 902 |
-
"Standard Deviation": 0.03908236317,
|
| 903 |
-
"Rank": 24
|
| 904 |
-
},
|
| 905 |
-
"Algebra": {
|
| 906 |
-
"Average Score": 0.582702645,
|
| 907 |
-
"Standard Deviation": 0.05002277711,
|
| 908 |
-
"Rank": 19
|
| 909 |
-
},
|
| 910 |
-
"Probability": {
|
| 911 |
-
"Average Score": 0.495001149,
|
| 912 |
-
"Standard Deviation": 0.05244587037,
|
| 913 |
-
"Rank": 21
|
| 914 |
-
},
|
| 915 |
-
"Logical": {
|
| 916 |
-
"Average Score": 0.443030561,
|
| 917 |
-
"Standard Deviation": 0.01343820628,
|
| 918 |
-
"Rank": 25
|
| 919 |
-
},
|
| 920 |
-
"Social": {
|
| 921 |
-
"Average Score": 0.329195941,
|
| 922 |
-
"Standard Deviation": 0.03925019528,
|
| 923 |
-
"Rank": 29
|
| 924 |
-
},
|
| 925 |
-
"Chemistry": {
|
| 926 |
-
"Average Score": 44.41846841004584,
|
| 927 |
-
"Standard Deviation": null,
|
| 928 |
-
"Rank": 26
|
| 929 |
-
}
|
| 930 |
-
}
|
| 931 |
-
},
|
| 932 |
-
{
|
| 933 |
-
"config": {
|
| 934 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 935 |
-
"organization": "OpenAI",
|
| 936 |
-
"license": "Proprietary",
|
| 937 |
-
"knowledge_cutoff": "2021/09"
|
| 938 |
-
},
|
| 939 |
-
"results": {
|
| 940 |
-
"OVERALL": {
|
| 941 |
-
"Average Score": 0.313398088,
|
| 942 |
-
"Standard Deviation": 0.09322528606,
|
| 943 |
-
"Rank": 40
|
| 944 |
-
},
|
| 945 |
-
"Geometry": {
|
| 946 |
-
"Average Score": 0.678714519,
|
| 947 |
-
"Standard Deviation": 0.05926546762,
|
| 948 |
-
"Rank": 13
|
| 949 |
-
},
|
| 950 |
-
"Algebra": {
|
| 951 |
-
"Average Score": 0.569296173,
|
| 952 |
-
"Standard Deviation": 0.05277281097,
|
| 953 |
-
"Rank": 20
|
| 954 |
-
},
|
| 955 |
-
"Probability": {
|
| 956 |
-
"Average Score": 0.448460767,
|
| 957 |
-
"Standard Deviation": 0.05768095196,
|
| 958 |
-
"Rank": 25
|
| 959 |
-
},
|
| 960 |
-
"Logical": {
|
| 961 |
-
"Average Score": 0.148521348,
|
| 962 |
-
"Standard Deviation": 0.04033712907,
|
| 963 |
-
"Rank": 45
|
| 964 |
-
},
|
| 965 |
-
"Social": {
|
| 966 |
-
"Average Score": 0.235071541,
|
| 967 |
-
"Standard Deviation": 0.02632892457,
|
| 968 |
-
"Rank": 38
|
| 969 |
-
},
|
| 970 |
-
"Chemistry": {
|
| 971 |
-
"Average Score": 40.46958736582551,
|
| 972 |
-
"Standard Deviation": null,
|
| 973 |
-
"Rank": 29
|
| 974 |
-
}
|
| 975 |
-
}
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"config": {
|
| 979 |
-
"model_name": "llama-3-70b-instruct",
|
| 980 |
-
"organization": "Meta",
|
| 981 |
-
"license": "Llama 3 Community",
|
| 982 |
-
"knowledge_cutoff": "2023/12"
|
| 983 |
-
},
|
| 984 |
-
"results": {
|
| 985 |
-
"OVERALL": {
|
| 986 |
-
"Average Score": 0.456689885,
|
| 987 |
-
"Standard Deviation": 0.01385989995,
|
| 988 |
-
"Rank": 23
|
| 989 |
-
},
|
| 990 |
-
"Geometry": {
|
| 991 |
-
"Average Score": 0.516865529,
|
| 992 |
-
"Standard Deviation": 0.03858112564,
|
| 993 |
-
"Rank": 25
|
| 994 |
-
},
|
| 995 |
-
"Algebra": {
|
| 996 |
-
"Average Score": 0.566756531,
|
| 997 |
-
"Standard Deviation": 0.03369826926,
|
| 998 |
-
"Rank": 21
|
| 999 |
-
},
|
| 1000 |
-
"Probability": {
|
| 1001 |
-
"Average Score": 0.513857306,
|
| 1002 |
-
"Standard Deviation": 0.05453699062,
|
| 1003 |
-
"Rank": 20
|
| 1004 |
-
},
|
| 1005 |
-
"Logical": {
|
| 1006 |
-
"Average Score": 0.713796415,
|
| 1007 |
-
"Standard Deviation": 0.02031215107,
|
| 1008 |
-
"Rank": 9
|
| 1009 |
-
},
|
| 1010 |
-
"Social": {
|
| 1011 |
-
"Average Score": 0.45872939,
|
| 1012 |
-
"Standard Deviation": 0.05347039576,
|
| 1013 |
-
"Rank": 21
|
| 1014 |
-
},
|
| 1015 |
-
"Chemistry": {
|
| 1016 |
-
"Average Score": 65.32140697218945,
|
| 1017 |
-
"Standard Deviation": null,
|
| 1018 |
-
"Rank": 13
|
| 1019 |
-
}
|
| 1020 |
-
}
|
| 1021 |
-
},
|
| 1022 |
-
{
|
| 1023 |
-
"config": {
|
| 1024 |
-
"model_name": "claude-3-sonnet",
|
| 1025 |
-
"organization": "Anthropic",
|
| 1026 |
-
"license": "Proprietary",
|
| 1027 |
-
"knowledge_cutoff": "2023/08"
|
| 1028 |
-
},
|
| 1029 |
-
"results": {
|
| 1030 |
-
"OVERALL": {
|
| 1031 |
-
"Average Score": 0.520010833,
|
| 1032 |
-
"Standard Deviation": 0.005030563799,
|
| 1033 |
-
"Rank": 17
|
| 1034 |
-
},
|
| 1035 |
-
"Geometry": {
|
| 1036 |
-
"Average Score": 0.675613638,
|
| 1037 |
-
"Standard Deviation": 0.05275594408,
|
| 1038 |
-
"Rank": 14
|
| 1039 |
-
},
|
| 1040 |
-
"Algebra": {
|
| 1041 |
-
"Average Score": 0.552025728,
|
| 1042 |
-
"Standard Deviation": 0.04122192409,
|
| 1043 |
-
"Rank": 22
|
| 1044 |
-
},
|
| 1045 |
-
"Probability": {
|
| 1046 |
-
"Average Score": 0.516192848,
|
| 1047 |
-
"Standard Deviation": 0.04152293217,
|
| 1048 |
-
"Rank": 19
|
| 1049 |
-
},
|
| 1050 |
-
"Logical": {
|
| 1051 |
-
"Average Score": 0.588545747,
|
| 1052 |
-
"Standard Deviation": 0.06068211943,
|
| 1053 |
-
"Rank": 17
|
| 1054 |
-
},
|
| 1055 |
-
"Social": {
|
| 1056 |
-
"Average Score": 0.570437582,
|
| 1057 |
-
"Standard Deviation": 0.08607040862,
|
| 1058 |
-
"Rank": 14
|
| 1059 |
-
},
|
| 1060 |
-
"Chemistry": {
|
| 1061 |
-
"Average Score": 61.33538592327427,
|
| 1062 |
-
"Standard Deviation": null,
|
| 1063 |
-
"Rank": 15
|
| 1064 |
-
}
|
| 1065 |
-
}
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"config": {
|
| 1069 |
-
"model_name": "qwen1.5-14b-chat",
|
| 1070 |
-
"organization": "Alibaba",
|
| 1071 |
-
"license": "Qianwen LICENSE",
|
| 1072 |
-
"knowledge_cutoff": "2024/02"
|
| 1073 |
-
},
|
| 1074 |
-
"results": {
|
| 1075 |
-
"OVERALL": {
|
| 1076 |
-
"Average Score": 0.415328996,
|
| 1077 |
-
"Standard Deviation": 0.0743938717,
|
| 1078 |
-
"Rank": 28
|
| 1079 |
-
},
|
| 1080 |
-
"Geometry": {
|
| 1081 |
-
"Average Score": 0.452504016,
|
| 1082 |
-
"Standard Deviation": 0.04225594393,
|
| 1083 |
-
"Rank": 27
|
| 1084 |
-
},
|
| 1085 |
-
"Algebra": {
|
| 1086 |
-
"Average Score": 0.538655725,
|
| 1087 |
-
"Standard Deviation": 0.03721542594,
|
| 1088 |
-
"Rank": 23
|
| 1089 |
-
},
|
| 1090 |
-
"Probability": {
|
| 1091 |
-
"Average Score": 0.397185975,
|
| 1092 |
-
"Standard Deviation": 0.05607695946,
|
| 1093 |
-
"Rank": 29
|
| 1094 |
-
},
|
| 1095 |
-
"Logical": {
|
| 1096 |
-
"Average Score": 0.264573129,
|
| 1097 |
-
"Standard Deviation": 0.03936133174,
|
| 1098 |
-
"Rank": 35
|
| 1099 |
-
},
|
| 1100 |
-
"Social": {
|
| 1101 |
-
"Average Score": 0.287370142,
|
| 1102 |
-
"Standard Deviation": 0.04264085315,
|
| 1103 |
-
"Rank": 31
|
| 1104 |
-
},
|
| 1105 |
-
"Chemistry": {
|
| 1106 |
-
"Average Score": 38.552779976347026,
|
| 1107 |
-
"Standard Deviation": null,
|
| 1108 |
-
"Rank": 31
|
| 1109 |
-
}
|
| 1110 |
-
}
|
| 1111 |
-
},
|
| 1112 |
-
{
|
| 1113 |
-
"config": {
|
| 1114 |
-
"model_name": "claude-3-haiku",
|
| 1115 |
-
"organization": "Anthropic",
|
| 1116 |
-
"license": "Proprietary",
|
| 1117 |
-
"knowledge_cutoff": "2023/08"
|
| 1118 |
-
},
|
| 1119 |
-
"results": {
|
| 1120 |
-
"OVERALL": {
|
| 1121 |
-
"Average Score": 0.453901163,
|
| 1122 |
-
"Standard Deviation": 0.003604084261,
|
| 1123 |
-
"Rank": 24
|
| 1124 |
-
},
|
| 1125 |
-
"Geometry": {
|
| 1126 |
-
"Average Score": 0.607993912,
|
| 1127 |
-
"Standard Deviation": 0.05793460748,
|
| 1128 |
-
"Rank": 16
|
| 1129 |
-
},
|
| 1130 |
-
"Algebra": {
|
| 1131 |
-
"Average Score": 0.520054055,
|
| 1132 |
-
"Standard Deviation": 0.03333544511,
|
| 1133 |
-
"Rank": 24
|
| 1134 |
-
},
|
| 1135 |
-
"Probability": {
|
| 1136 |
-
"Average Score": 0.474460688,
|
| 1137 |
-
"Standard Deviation": 0.0446501933,
|
| 1138 |
-
"Rank": 24
|
| 1139 |
-
},
|
| 1140 |
-
"Logical": {
|
| 1141 |
-
"Average Score": 0.512815976,
|
| 1142 |
-
"Standard Deviation": 0.0163264281,
|
| 1143 |
-
"Rank": 21
|
| 1144 |
-
},
|
| 1145 |
-
"Social": {
|
| 1146 |
-
"Average Score": 0.551083976,
|
| 1147 |
-
"Standard Deviation": 0.05374722539,
|
| 1148 |
-
"Rank": 16
|
| 1149 |
-
},
|
| 1150 |
-
"Chemistry": {
|
| 1151 |
-
"Average Score": 56.40200048817984,
|
| 1152 |
-
"Standard Deviation": null,
|
| 1153 |
-
"Rank": 16
|
| 1154 |
-
}
|
| 1155 |
-
}
|
| 1156 |
-
},
|
| 1157 |
-
{
|
| 1158 |
-
"config": {
|
| 1159 |
-
"model_name": "claude-2.1",
|
| 1160 |
-
"organization": "Anthropic",
|
| 1161 |
-
"license": "Proprietary",
|
| 1162 |
-
"knowledge_cutoff": "Unknown"
|
| 1163 |
-
},
|
| 1164 |
-
"results": {
|
| 1165 |
-
"OVERALL": {
|
| 1166 |
-
"Average Score": 0.35814708,
|
| 1167 |
-
"Standard Deviation": 0.09168134168,
|
| 1168 |
-
"Rank": 36
|
| 1169 |
-
},
|
| 1170 |
-
"Geometry": {
|
| 1171 |
-
"Average Score": 0.62752395,
|
| 1172 |
-
"Standard Deviation": 0.07232659398,
|
| 1173 |
-
"Rank": 15
|
| 1174 |
-
},
|
| 1175 |
-
"Algebra": {
|
| 1176 |
-
"Average Score": 0.508849609,
|
| 1177 |
-
"Standard Deviation": 0.0346897465,
|
| 1178 |
-
"Rank": 25
|
| 1179 |
-
},
|
| 1180 |
-
"Probability": {
|
| 1181 |
-
"Average Score": 0.41477086,
|
| 1182 |
-
"Standard Deviation": 0.05964060239,
|
| 1183 |
-
"Rank": 28
|
| 1184 |
-
},
|
| 1185 |
-
"Logical": {
|
| 1186 |
-
"Average Score": 0.482923674,
|
| 1187 |
-
"Standard Deviation": 0.01989147048,
|
| 1188 |
-
"Rank": 22
|
| 1189 |
-
},
|
| 1190 |
-
"Social": {
|
| 1191 |
-
"Average Score": 0.333804568,
|
| 1192 |
-
"Standard Deviation": 0.03775548253,
|
| 1193 |
-
"Rank": 28
|
| 1194 |
-
},
|
| 1195 |
-
"Chemistry": {
|
| 1196 |
-
"Average Score": 47.23672563994903,
|
| 1197 |
-
"Standard Deviation": null,
|
| 1198 |
-
"Rank": 21
|
| 1199 |
-
}
|
| 1200 |
-
}
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"config": {
|
| 1204 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 1205 |
-
"organization": "Mistral",
|
| 1206 |
-
"license": "Apache 2.0",
|
| 1207 |
-
"knowledge_cutoff": "2023/12"
|
| 1208 |
-
},
|
| 1209 |
-
"results": {
|
| 1210 |
-
"OVERALL": {
|
| 1211 |
-
"Average Score": 0.382659161,
|
| 1212 |
-
"Standard Deviation": 0.07594496929,
|
| 1213 |
-
"Rank": 31
|
| 1214 |
-
},
|
| 1215 |
-
"Geometry": {
|
| 1216 |
-
"Average Score": 0.432216097,
|
| 1217 |
-
"Standard Deviation": 0.04747949254,
|
| 1218 |
-
"Rank": 30
|
| 1219 |
-
},
|
| 1220 |
-
"Algebra": {
|
| 1221 |
-
"Average Score": 0.478314888,
|
| 1222 |
-
"Standard Deviation": 0.01998797419,
|
| 1223 |
-
"Rank": 26
|
| 1224 |
-
},
|
| 1225 |
-
"Probability": {
|
| 1226 |
-
"Average Score": 0.427144725,
|
| 1227 |
-
"Standard Deviation": 0.0590923329,
|
| 1228 |
-
"Rank": 27
|
| 1229 |
-
},
|
| 1230 |
-
"Logical": {
|
| 1231 |
-
"Average Score": 0.340041983,
|
| 1232 |
-
"Standard Deviation": 0.008397574592,
|
| 1233 |
-
"Rank": 28
|
| 1234 |
-
},
|
| 1235 |
-
"Social": {
|
| 1236 |
-
"Average Score": 0.251949622,
|
| 1237 |
-
"Standard Deviation": 0.03346674405,
|
| 1238 |
-
"Rank": 36
|
| 1239 |
-
},
|
| 1240 |
-
"Chemistry": {
|
| 1241 |
-
"Average Score": 44.533118241976666,
|
| 1242 |
-
"Standard Deviation": null,
|
| 1243 |
-
"Rank": 25
|
| 1244 |
-
}
|
| 1245 |
-
}
|
| 1246 |
-
},
|
| 1247 |
-
{
|
| 1248 |
-
"config": {
|
| 1249 |
-
"model_name": "claude-2.0",
|
| 1250 |
-
"organization": "Anthropic",
|
| 1251 |
-
"license": "Proprietary",
|
| 1252 |
-
"knowledge_cutoff": "Unknown"
|
| 1253 |
-
},
|
| 1254 |
-
"results": {
|
| 1255 |
-
"OVERALL": {
|
| 1256 |
-
"Average Score": 0.322718057,
|
| 1257 |
-
"Standard Deviation": 0.08369883584,
|
| 1258 |
-
"Rank": 38
|
| 1259 |
-
},
|
| 1260 |
-
"Geometry": {
|
| 1261 |
-
"Average Score": 0.604141967,
|
| 1262 |
-
"Standard Deviation": 0.05116441826,
|
| 1263 |
-
"Rank": 17
|
| 1264 |
-
},
|
| 1265 |
-
"Algebra": {
|
| 1266 |
-
"Average Score": 0.474350734,
|
| 1267 |
-
"Standard Deviation": 0.01510393066,
|
| 1268 |
-
"Rank": 27
|
| 1269 |
-
},
|
| 1270 |
-
"Probability": {
|
| 1271 |
-
"Average Score": 0.437950412,
|
| 1272 |
-
"Standard Deviation": 0.05985594317,
|
| 1273 |
-
"Rank": 26
|
| 1274 |
-
},
|
| 1275 |
-
"Logical": {
|
| 1276 |
-
"Average Score": 0.445620646,
|
| 1277 |
-
"Standard Deviation": 0.01812614805,
|
| 1278 |
-
"Rank": 24
|
| 1279 |
-
},
|
| 1280 |
-
"Social": {
|
| 1281 |
-
"Average Score": 0.469422836,
|
| 1282 |
-
"Standard Deviation": 0.05999901796,
|
| 1283 |
-
"Rank": 19
|
| 1284 |
-
},
|
| 1285 |
-
"Chemistry": {
|
| 1286 |
-
"Average Score": 50.773143448036464,
|
| 1287 |
-
"Standard Deviation": null,
|
| 1288 |
-
"Rank": 19
|
| 1289 |
-
}
|
| 1290 |
-
}
|
| 1291 |
-
},
|
| 1292 |
-
{
|
| 1293 |
-
"config": {
|
| 1294 |
-
"model_name": "starling-lm-7b-beta",
|
| 1295 |
-
"organization": "Nexusflow",
|
| 1296 |
-
"license": "Apache-2.0",
|
| 1297 |
-
"knowledge_cutoff": "2024/03"
|
| 1298 |
-
},
|
| 1299 |
-
"results": {
|
| 1300 |
-
"OVERALL": {
|
| 1301 |
-
"Average Score": 0.479391856,
|
| 1302 |
-
"Standard Deviation": 0.04199990887,
|
| 1303 |
-
"Rank": 22
|
| 1304 |
-
},
|
| 1305 |
-
"Geometry": {
|
| 1306 |
-
"Average Score": 0.446654388,
|
| 1307 |
-
"Standard Deviation": 0.05637864999,
|
| 1308 |
-
"Rank": 29
|
| 1309 |
-
},
|
| 1310 |
-
"Algebra": {
|
| 1311 |
-
"Average Score": 0.473952749,
|
| 1312 |
-
"Standard Deviation": 0.01584301288,
|
| 1313 |
-
"Rank": 28
|
| 1314 |
-
},
|
| 1315 |
-
"Probability": {
|
| 1316 |
-
"Average Score": 0.395197837,
|
| 1317 |
-
"Standard Deviation": 0.05814798892,
|
| 1318 |
-
"Rank": 30
|
| 1319 |
-
},
|
| 1320 |
-
"Logical": {
|
| 1321 |
-
"Average Score": 0.39927199,
|
| 1322 |
-
"Standard Deviation": 0.02125277518,
|
| 1323 |
-
"Rank": 26
|
| 1324 |
-
},
|
| 1325 |
-
"Social": {
|
| 1326 |
-
"Average Score": 0.380021662,
|
| 1327 |
-
"Standard Deviation": 0.04622452748,
|
| 1328 |
-
"Rank": 26
|
| 1329 |
-
},
|
| 1330 |
-
"Chemistry": {
|
| 1331 |
-
"Average Score": 38.27587102395908,
|
| 1332 |
-
"Standard Deviation": null,
|
| 1333 |
-
"Rank": 32
|
| 1334 |
-
}
|
| 1335 |
-
}
|
| 1336 |
-
},
|
| 1337 |
-
{
|
| 1338 |
-
"config": {
|
| 1339 |
-
"model_name": "gemini-1.0-pro-001",
|
| 1340 |
-
"organization": "Google",
|
| 1341 |
-
"license": "Proprietary",
|
| 1342 |
-
"knowledge_cutoff": "2023/04"
|
| 1343 |
-
},
|
| 1344 |
-
"results": {
|
| 1345 |
-
"OVERALL": {
|
| 1346 |
-
"Average Score": 0.449040654,
|
| 1347 |
-
"Standard Deviation": 0.0450610177,
|
| 1348 |
-
"Rank": 25
|
| 1349 |
-
},
|
| 1350 |
-
"Geometry": {
|
| 1351 |
-
"Average Score": 0.578347959,
|
| 1352 |
-
"Standard Deviation": 0.04242873607,
|
| 1353 |
-
"Rank": 20
|
| 1354 |
-
},
|
| 1355 |
-
"Algebra": {
|
| 1356 |
-
"Average Score": 0.462417786,
|
| 1357 |
-
"Standard Deviation": 0.01668313635,
|
| 1358 |
-
"Rank": 29
|
| 1359 |
-
},
|
| 1360 |
-
"Probability": {
|
| 1361 |
-
"Average Score": 0.289836324,
|
| 1362 |
-
"Standard Deviation": 0.05739831115,
|
| 1363 |
-
"Rank": 38
|
| 1364 |
-
},
|
| 1365 |
-
"Logical": {
|
| 1366 |
-
"Average Score": 0.191140355,
|
| 1367 |
-
"Standard Deviation": 0.03394652499,
|
| 1368 |
-
"Rank": 41
|
| 1369 |
-
},
|
| 1370 |
-
"Social": {
|
| 1371 |
-
"Average Score": 0.130790863,
|
| 1372 |
-
"Standard Deviation": 0.02800188173,
|
| 1373 |
-
"Rank": 46
|
| 1374 |
-
},
|
| 1375 |
-
"Chemistry": {
|
| 1376 |
-
"Average Score": 45.22204471452975,
|
| 1377 |
-
"Standard Deviation": null,
|
| 1378 |
-
"Rank": 23
|
| 1379 |
-
}
|
| 1380 |
-
}
|
| 1381 |
-
},
|
| 1382 |
-
{
|
| 1383 |
-
"config": {
|
| 1384 |
-
"model_name": "openchat-3.5-0106",
|
| 1385 |
-
"organization": "OpenChat",
|
| 1386 |
-
"license": "Apache-2.0",
|
| 1387 |
-
"knowledge_cutoff": "2024/01"
|
| 1388 |
-
},
|
| 1389 |
-
"results": {
|
| 1390 |
-
"OVERALL": {
|
| 1391 |
-
"Average Score": 0.363929888,
|
| 1392 |
-
"Standard Deviation": 0.08602347145,
|
| 1393 |
-
"Rank": 34
|
| 1394 |
-
},
|
| 1395 |
-
"Geometry": {
|
| 1396 |
-
"Average Score": 0.38715246,
|
| 1397 |
-
"Standard Deviation": 0.03701851946,
|
| 1398 |
-
"Rank": 33
|
| 1399 |
-
},
|
| 1400 |
-
"Algebra": {
|
| 1401 |
-
"Average Score": 0.441233712,
|
| 1402 |
-
"Standard Deviation": 0.01135753754,
|
| 1403 |
-
"Rank": 30
|
| 1404 |
-
},
|
| 1405 |
-
"Probability": {
|
| 1406 |
-
"Average Score": 0.38802618,
|
| 1407 |
-
"Standard Deviation": 0.05663879714,
|
| 1408 |
-
"Rank": 31
|
| 1409 |
-
},
|
| 1410 |
-
"Logical": {
|
| 1411 |
-
"Average Score": 0.336754383,
|
| 1412 |
-
"Standard Deviation": 0.01608478079,
|
| 1413 |
-
"Rank": 29
|
| 1414 |
-
},
|
| 1415 |
-
"Social": {
|
| 1416 |
-
"Average Score": 0.250891608,
|
| 1417 |
-
"Standard Deviation": 0.03253769914,
|
| 1418 |
-
"Rank": 37
|
| 1419 |
-
},
|
| 1420 |
-
"Chemistry": {
|
| 1421 |
-
"Average Score": 33.70639271807677,
|
| 1422 |
-
"Standard Deviation": null,
|
| 1423 |
-
"Rank": 33
|
| 1424 |
-
}
|
| 1425 |
-
}
|
| 1426 |
-
},
|
| 1427 |
-
{
|
| 1428 |
-
"config": {
|
| 1429 |
-
"model_name": "openchat-3.5",
|
| 1430 |
-
"organization": "OpenChat",
|
| 1431 |
-
"license": "Apache-2.0",
|
| 1432 |
-
"knowledge_cutoff": "2023/11"
|
| 1433 |
-
},
|
| 1434 |
-
"results": {
|
| 1435 |
-
"OVERALL": {
|
| 1436 |
-
"Average Score": 0.361341296,
|
| 1437 |
-
"Standard Deviation": 0.09034869493,
|
| 1438 |
-
"Rank": 35
|
| 1439 |
-
},
|
| 1440 |
-
"Geometry": {
|
| 1441 |
-
"Average Score": 0.401699069,
|
| 1442 |
-
"Standard Deviation": 0.03410726557,
|
| 1443 |
-
"Rank": 31
|
| 1444 |
-
},
|
| 1445 |
-
"Algebra": {
|
| 1446 |
-
"Average Score": 0.414095336,
|
| 1447 |
-
"Standard Deviation": 0.01881964261,
|
| 1448 |
-
"Rank": 32
|
| 1449 |
-
},
|
| 1450 |
-
"Probability": {
|
| 1451 |
-
"Average Score": 0.349601002,
|
| 1452 |
-
"Standard Deviation": 0.05077455539,
|
| 1453 |
-
"Rank": 33
|
| 1454 |
-
},
|
| 1455 |
-
"Logical": {
|
| 1456 |
-
"Average Score": 0.331069242,
|
| 1457 |
-
"Standard Deviation": 0.02180827173,
|
| 1458 |
-
"Rank": 31
|
| 1459 |
-
},
|
| 1460 |
-
"Social": {
|
| 1461 |
-
"Average Score": 0.319991655,
|
| 1462 |
-
"Standard Deviation": 0.04502478724,
|
| 1463 |
-
"Rank": 30
|
| 1464 |
-
},
|
| 1465 |
-
"Chemistry": {
|
| 1466 |
-
"Average Score": 33.020911255646965,
|
| 1467 |
-
"Standard Deviation": null,
|
| 1468 |
-
"Rank": 34
|
| 1469 |
-
}
|
| 1470 |
-
}
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"config": {
|
| 1474 |
-
"model_name": "command-r-(08-2024)",
|
| 1475 |
-
"organization": "Cohere",
|
| 1476 |
-
"license": "CC-BY-NC-4.0",
|
| 1477 |
-
"knowledge_cutoff": "2024/08"
|
| 1478 |
-
},
|
| 1479 |
-
"results": {
|
| 1480 |
-
"OVERALL": {
|
| 1481 |
-
"Average Score": 0.427605298,
|
| 1482 |
-
"Standard Deviation": 0.01747449163,
|
| 1483 |
-
"Rank": 26
|
| 1484 |
-
},
|
| 1485 |
-
"Geometry": {
|
| 1486 |
-
"Average Score": 0.448300727,
|
| 1487 |
-
"Standard Deviation": 0.04996362328,
|
| 1488 |
-
"Rank": 28
|
| 1489 |
-
},
|
| 1490 |
-
"Algebra": {
|
| 1491 |
-
"Average Score": 0.417519167,
|
| 1492 |
-
"Standard Deviation": 0.01822196902,
|
| 1493 |
-
"Rank": 31
|
| 1494 |
-
},
|
| 1495 |
-
"Probability": {
|
| 1496 |
-
"Average Score": 0.366336281,
|
| 1497 |
-
"Standard Deviation": 0.04716826942,
|
| 1498 |
-
"Rank": 32
|
| 1499 |
-
},
|
| 1500 |
-
"Logical": {
|
| 1501 |
-
"Average Score": 0.214657906,
|
| 1502 |
-
"Standard Deviation": 0.03003579835,
|
| 1503 |
-
"Rank": 38
|
| 1504 |
-
},
|
| 1505 |
-
"Social": {
|
| 1506 |
-
"Average Score": 0.276088379,
|
| 1507 |
-
"Standard Deviation": 0.03295234688,
|
| 1508 |
-
"Rank": 33
|
| 1509 |
-
},
|
| 1510 |
-
"Chemistry": {
|
| 1511 |
-
"Average Score": 39.61492485677676,
|
| 1512 |
-
"Standard Deviation": null,
|
| 1513 |
-
"Rank": 30
|
| 1514 |
-
}
|
| 1515 |
-
}
|
| 1516 |
-
},
|
| 1517 |
-
{
|
| 1518 |
-
"config": {
|
| 1519 |
-
"model_name": "gemma-1.1-7b-it",
|
| 1520 |
-
"organization": "Google",
|
| 1521 |
-
"license": "Gemma License",
|
| 1522 |
-
"knowledge_cutoff": "2024/02"
|
| 1523 |
-
},
|
| 1524 |
-
"results": {
|
| 1525 |
-
"OVERALL": {
|
| 1526 |
-
"Average Score": 0.339506922,
|
| 1527 |
-
"Standard Deviation": 0.1066279108,
|
| 1528 |
-
"Rank": 37
|
| 1529 |
-
},
|
| 1530 |
-
"Geometry": {
|
| 1531 |
-
"Average Score": 0.324170977,
|
| 1532 |
-
"Standard Deviation": 0.04668553765,
|
| 1533 |
-
"Rank": 36
|
| 1534 |
-
},
|
| 1535 |
-
"Algebra": {
|
| 1536 |
-
"Average Score": 0.398684697,
|
| 1537 |
-
"Standard Deviation": 0.01982398259,
|
| 1538 |
-
"Rank": 33
|
| 1539 |
-
},
|
| 1540 |
-
"Probability": {
|
| 1541 |
-
"Average Score": 0.293253175,
|
| 1542 |
-
"Standard Deviation": 0.05126192191,
|
| 1543 |
-
"Rank": 37
|
| 1544 |
-
},
|
| 1545 |
-
"Logical": {
|
| 1546 |
-
"Average Score": 0.317750796,
|
| 1547 |
-
"Standard Deviation": 0.01101933543,
|
| 1548 |
-
"Rank": 32
|
| 1549 |
-
},
|
| 1550 |
-
"Social": {
|
| 1551 |
-
"Average Score": 0.179073276,
|
| 1552 |
-
"Standard Deviation": 0.02009658805,
|
| 1553 |
-
"Rank": 42
|
| 1554 |
-
},
|
| 1555 |
-
"Chemistry": {
|
| 1556 |
-
"Average Score": 42.666504105798204,
|
| 1557 |
-
"Standard Deviation": null,
|
| 1558 |
-
"Rank": 27
|
| 1559 |
-
}
|
| 1560 |
-
}
|
| 1561 |
-
},
|
| 1562 |
-
{
|
| 1563 |
-
"config": {
|
| 1564 |
-
"model_name": "llama3-8b-instruct",
|
| 1565 |
-
"organization": "Meta",
|
| 1566 |
-
"license": "Llama 3 Community",
|
| 1567 |
-
"knowledge_cutoff": "2023/03"
|
| 1568 |
-
},
|
| 1569 |
-
"results": {
|
| 1570 |
-
"OVERALL": {
|
| 1571 |
-
"Average Score": 0.367722676,
|
| 1572 |
-
"Standard Deviation": 0.1071368221,
|
| 1573 |
-
"Rank": 32
|
| 1574 |
-
},
|
| 1575 |
-
"Geometry": {
|
| 1576 |
-
"Average Score": 0.367143758,
|
| 1577 |
-
"Standard Deviation": 0.04363680358,
|
| 1578 |
-
"Rank": 34
|
| 1579 |
-
},
|
| 1580 |
-
"Algebra": {
|
| 1581 |
-
"Average Score": 0.391480973,
|
| 1582 |
-
"Standard Deviation": 0.02757445266,
|
| 1583 |
-
"Rank": 34
|
| 1584 |
-
},
|
| 1585 |
-
"Probability": {
|
| 1586 |
-
"Average Score": 0.317616445,
|
| 1587 |
-
"Standard Deviation": 0.04300430361,
|
| 1588 |
-
"Rank": 36
|
| 1589 |
-
},
|
| 1590 |
-
"Logical": {
|
| 1591 |
-
"Average Score": 0.461607495,
|
| 1592 |
-
"Standard Deviation": 0.02185028842,
|
| 1593 |
-
"Rank": 23
|
| 1594 |
-
},
|
| 1595 |
-
"Social": {
|
| 1596 |
-
"Average Score": 0.336373622,
|
| 1597 |
-
"Standard Deviation": 0.05762408512,
|
| 1598 |
-
"Rank": 27
|
| 1599 |
-
},
|
| 1600 |
-
"Chemistry": {
|
| 1601 |
-
"Average Score": 45.35392139264795,
|
| 1602 |
-
"Standard Deviation": null,
|
| 1603 |
-
"Rank": 22
|
| 1604 |
-
}
|
| 1605 |
-
}
|
| 1606 |
-
},
|
| 1607 |
-
{
|
| 1608 |
-
"config": {
|
| 1609 |
-
"model_name": "gemma-2-2b-it",
|
| 1610 |
-
"organization": "Google",
|
| 1611 |
-
"license": "Gemma License",
|
| 1612 |
-
"knowledge_cutoff": "2024/07"
|
| 1613 |
-
},
|
| 1614 |
-
"results": {
|
| 1615 |
-
"OVERALL": {
|
| 1616 |
-
"Average Score": 0.502167612,
|
| 1617 |
-
"Standard Deviation": 0.04389786763,
|
| 1618 |
-
"Rank": 20
|
| 1619 |
-
},
|
| 1620 |
-
"Geometry": {
|
| 1621 |
-
"Average Score": 0.395006676,
|
| 1622 |
-
"Standard Deviation": 0.05882607713,
|
| 1623 |
-
"Rank": 32
|
| 1624 |
-
},
|
| 1625 |
-
"Algebra": {
|
| 1626 |
-
"Average Score": 0.379391887,
|
| 1627 |
-
"Standard Deviation": 0.01722410785,
|
| 1628 |
-
"Rank": 35
|
| 1629 |
-
},
|
| 1630 |
-
"Probability": {
|
| 1631 |
-
"Average Score": 0.331231097,
|
| 1632 |
-
"Standard Deviation": 0.05392499987,
|
| 1633 |
-
"Rank": 35
|
| 1634 |
-
},
|
| 1635 |
-
"Logical": {
|
| 1636 |
-
"Average Score": 0.367687789,
|
| 1637 |
-
"Standard Deviation": 0.02547968808,
|
| 1638 |
-
"Rank": 27
|
| 1639 |
-
},
|
| 1640 |
-
"Social": {
|
| 1641 |
-
"Average Score": 0.393482094,
|
| 1642 |
-
"Standard Deviation": 0.06450214024,
|
| 1643 |
-
"Rank": 24
|
| 1644 |
-
},
|
| 1645 |
-
"Chemistry": {
|
| 1646 |
-
"Average Score": 30.53406933106768,
|
| 1647 |
-
"Standard Deviation": null,
|
| 1648 |
-
"Rank": 36
|
| 1649 |
-
}
|
| 1650 |
-
}
|
| 1651 |
-
},
|
| 1652 |
-
{
|
| 1653 |
-
"config": {
|
| 1654 |
-
"model_name": "starling-lm-7b-alpha",
|
| 1655 |
-
"organization": "Nexusflow",
|
| 1656 |
-
"license": "Apache-2.0",
|
| 1657 |
-
"knowledge_cutoff": "2023/11"
|
| 1658 |
-
},
|
| 1659 |
-
"results": {
|
| 1660 |
-
"OVERALL": {
|
| 1661 |
-
"Average Score": 0.366628765,
|
| 1662 |
-
"Standard Deviation": 0.08405492929,
|
| 1663 |
-
"Rank": 33
|
| 1664 |
-
},
|
| 1665 |
-
"Geometry": {
|
| 1666 |
-
"Average Score": 0.336782578,
|
| 1667 |
-
"Standard Deviation": 0.04069449132,
|
| 1668 |
-
"Rank": 35
|
| 1669 |
-
},
|
| 1670 |
-
"Algebra": {
|
| 1671 |
-
"Average Score": 0.371551932,
|
| 1672 |
-
"Standard Deviation": 0.03367241745,
|
| 1673 |
-
"Rank": 36
|
| 1674 |
-
},
|
| 1675 |
-
"Probability": {
|
| 1676 |
-
"Average Score": 0.331472505,
|
| 1677 |
-
"Standard Deviation": 0.04833324282,
|
| 1678 |
-
"Rank": 34
|
| 1679 |
-
},
|
| 1680 |
-
"Logical": {
|
| 1681 |
-
"Average Score": 0.260869624,
|
| 1682 |
-
"Standard Deviation": 0.03562735237,
|
| 1683 |
-
"Rank": 36
|
| 1684 |
-
},
|
| 1685 |
-
"Social": {
|
| 1686 |
-
"Average Score": 0.271975534,
|
| 1687 |
-
"Standard Deviation": 0.04266753408,
|
| 1688 |
-
"Rank": 34
|
| 1689 |
-
},
|
| 1690 |
-
"Chemistry": {
|
| 1691 |
-
"Average Score": 30.07926487356878,
|
| 1692 |
-
"Standard Deviation": null,
|
| 1693 |
-
"Rank": 37
|
| 1694 |
-
}
|
| 1695 |
-
}
|
| 1696 |
-
},
|
| 1697 |
-
{
|
| 1698 |
-
"config": {
|
| 1699 |
-
"model_name": "qwen1.5-4b-chat",
|
| 1700 |
-
"organization": "Alibaba",
|
| 1701 |
-
"license": "Qianwen LICENSE",
|
| 1702 |
-
"knowledge_cutoff": "2024/02"
|
| 1703 |
-
},
|
| 1704 |
-
"results": {
|
| 1705 |
-
"OVERALL": {
|
| 1706 |
-
"Average Score": 0.111876411,
|
| 1707 |
-
"Standard Deviation": 0.04241022785,
|
| 1708 |
-
"Rank": 49
|
| 1709 |
-
},
|
| 1710 |
-
"Geometry": {
|
| 1711 |
-
"Average Score": 0.215834522,
|
| 1712 |
-
"Standard Deviation": 0.0363766363,
|
| 1713 |
-
"Rank": 40
|
| 1714 |
-
},
|
| 1715 |
-
"Algebra": {
|
| 1716 |
-
"Average Score": 0.305589811,
|
| 1717 |
-
"Standard Deviation": 0.02354198912,
|
| 1718 |
-
"Rank": 37
|
| 1719 |
-
},
|
| 1720 |
-
"Probability": {
|
| 1721 |
-
"Average Score": 0.149365327,
|
| 1722 |
-
"Standard Deviation": 0.03489672675,
|
| 1723 |
-
"Rank": 44
|
| 1724 |
-
},
|
| 1725 |
-
"Logical": {
|
| 1726 |
-
"Average Score": 0.116210168,
|
| 1727 |
-
"Standard Deviation": 0.005927966496,
|
| 1728 |
-
"Rank": 47
|
| 1729 |
-
},
|
| 1730 |
-
"Social": {
|
| 1731 |
-
"Average Score": 0.18195615,
|
| 1732 |
-
"Standard Deviation": 0.02269805277,
|
| 1733 |
-
"Rank": 41
|
| 1734 |
-
},
|
| 1735 |
-
"Chemistry": {
|
| 1736 |
-
"Average Score": 13.21208067122554,
|
| 1737 |
-
"Standard Deviation": null,
|
| 1738 |
-
"Rank": 47
|
| 1739 |
-
}
|
| 1740 |
-
}
|
| 1741 |
-
},
|
| 1742 |
-
{
|
| 1743 |
-
"config": {
|
| 1744 |
-
"model_name": "command-r-(04-2024)",
|
| 1745 |
-
"organization": "Cohere",
|
| 1746 |
-
"license": "CC-BY-NC-4.0",
|
| 1747 |
-
"knowledge_cutoff": "2024/04"
|
| 1748 |
-
},
|
| 1749 |
-
"results": {
|
| 1750 |
-
"OVERALL": {
|
| 1751 |
-
"Average Score": 0.388783887,
|
| 1752 |
-
"Standard Deviation": 0.07417186783,
|
| 1753 |
-
"Rank": 30
|
| 1754 |
-
},
|
| 1755 |
-
"Geometry": {
|
| 1756 |
-
"Average Score": 0.300416698,
|
| 1757 |
-
"Standard Deviation": 0.03485612736,
|
| 1758 |
-
"Rank": 37
|
| 1759 |
-
},
|
| 1760 |
-
"Algebra": {
|
| 1761 |
-
"Average Score": 0.293120231,
|
| 1762 |
-
"Standard Deviation": 0.032926484,
|
| 1763 |
-
"Rank": 38
|
| 1764 |
-
},
|
| 1765 |
-
"Probability": {
|
| 1766 |
-
"Average Score": 0.281271304,
|
| 1767 |
-
"Standard Deviation": 0.05697149867,
|
| 1768 |
-
"Rank": 39
|
| 1769 |
-
},
|
| 1770 |
-
"Logical": {
|
| 1771 |
-
"Average Score": 0.276189906,
|
| 1772 |
-
"Standard Deviation": 0.03562914754,
|
| 1773 |
-
"Rank": 34
|
| 1774 |
-
},
|
| 1775 |
-
"Social": {
|
| 1776 |
-
"Average Score": 0.283882949,
|
| 1777 |
-
"Standard Deviation": 0.03336901148,
|
| 1778 |
-
"Rank": 32
|
| 1779 |
-
},
|
| 1780 |
-
"Chemistry": {
|
| 1781 |
-
"Average Score": 41.346336503003236,
|
| 1782 |
-
"Standard Deviation": null,
|
| 1783 |
-
"Rank": 28
|
| 1784 |
-
}
|
| 1785 |
-
}
|
| 1786 |
-
},
|
| 1787 |
-
{
|
| 1788 |
-
"config": {
|
| 1789 |
-
"model_name": "vicuna-33b",
|
| 1790 |
-
"organization": "LMSYS",
|
| 1791 |
-
"license": "Non-commercial",
|
| 1792 |
-
"knowledge_cutoff": "2023/08"
|
| 1793 |
-
},
|
| 1794 |
-
"results": {
|
| 1795 |
-
"OVERALL": {
|
| 1796 |
-
"Average Score": 0.316543555,
|
| 1797 |
-
"Standard Deviation": 0.08922095647,
|
| 1798 |
-
"Rank": 39
|
| 1799 |
-
},
|
| 1800 |
-
"Geometry": {
|
| 1801 |
-
"Average Score": 0.208284679,
|
| 1802 |
-
"Standard Deviation": 0.03937771461,
|
| 1803 |
-
"Rank": 41
|
| 1804 |
-
},
|
| 1805 |
-
"Algebra": {
|
| 1806 |
-
"Average Score": 0.248994048,
|
| 1807 |
-
"Standard Deviation": 0.02668175054,
|
| 1808 |
-
"Rank": 40
|
| 1809 |
-
},
|
| 1810 |
-
"Probability": {
|
| 1811 |
-
"Average Score": 0.222313995,
|
| 1812 |
-
"Standard Deviation": 0.03978859759,
|
| 1813 |
-
"Rank": 42
|
| 1814 |
-
},
|
| 1815 |
-
"Logical": {
|
| 1816 |
-
"Average Score": 0.180291222,
|
| 1817 |
-
"Standard Deviation": 0.021886267,
|
| 1818 |
-
"Rank": 42
|
| 1819 |
-
},
|
| 1820 |
-
"Social": {
|
| 1821 |
-
"Average Score": 0.257623798,
|
| 1822 |
-
"Standard Deviation": 0.02653724437,
|
| 1823 |
-
"Rank": 35
|
| 1824 |
-
},
|
| 1825 |
-
"Chemistry": {
|
| 1826 |
-
"Average Score": 28.01838653090379,
|
| 1827 |
-
"Standard Deviation": null,
|
| 1828 |
-
"Rank": 38
|
| 1829 |
-
}
|
| 1830 |
-
}
|
| 1831 |
-
},
|
| 1832 |
-
{
|
| 1833 |
-
"config": {
|
| 1834 |
-
"model_name": "gemma-7b-it",
|
| 1835 |
-
"organization": "Google",
|
| 1836 |
-
"license": "Gemma License",
|
| 1837 |
-
"knowledge_cutoff": "2024/02"
|
| 1838 |
-
},
|
| 1839 |
-
"results": {
|
| 1840 |
-
"OVERALL": {
|
| 1841 |
-
"Average Score": 0.285077558,
|
| 1842 |
-
"Standard Deviation": 0.08871758453,
|
| 1843 |
-
"Rank": 41
|
| 1844 |
-
},
|
| 1845 |
-
"Geometry": {
|
| 1846 |
-
"Average Score": 0.244791417,
|
| 1847 |
-
"Standard Deviation": 0.0289612078,
|
| 1848 |
-
"Rank": 38
|
| 1849 |
-
},
|
| 1850 |
-
"Algebra": {
|
| 1851 |
-
"Average Score": 0.250614794,
|
| 1852 |
-
"Standard Deviation": 0.01991678295,
|
| 1853 |
-
"Rank": 39
|
| 1854 |
-
},
|
| 1855 |
-
"Probability": {
|
| 1856 |
-
"Average Score": 0.174313053,
|
| 1857 |
-
"Standard Deviation": 0.03765424728,
|
| 1858 |
-
"Rank": 43
|
| 1859 |
-
},
|
| 1860 |
-
"Logical": {
|
| 1861 |
-
"Average Score": 0.197505536,
|
| 1862 |
-
"Standard Deviation": 0.02050298885,
|
| 1863 |
-
"Rank": 39
|
| 1864 |
-
},
|
| 1865 |
-
"Social": {
|
| 1866 |
-
"Average Score": 0.202138025,
|
| 1867 |
-
"Standard Deviation": 0.02098346639,
|
| 1868 |
-
"Rank": 40
|
| 1869 |
-
},
|
| 1870 |
-
"Chemistry": {
|
| 1871 |
-
"Average Score": 28.014658234926813,
|
| 1872 |
-
"Standard Deviation": null,
|
| 1873 |
-
"Rank": 39
|
| 1874 |
-
}
|
| 1875 |
-
}
|
| 1876 |
-
},
|
| 1877 |
-
{
|
| 1878 |
-
"config": {
|
| 1879 |
-
"model_name": "mistral-7b-instruct-2",
|
| 1880 |
-
"organization": "Mistral",
|
| 1881 |
-
"license": "Apache 2.0",
|
| 1882 |
-
"knowledge_cutoff": "2023/12"
|
| 1883 |
-
},
|
| 1884 |
-
"results": {
|
| 1885 |
-
"OVERALL": {
|
| 1886 |
-
"Average Score": 0.427513868,
|
| 1887 |
-
"Standard Deviation": 0.05553921135,
|
| 1888 |
-
"Rank": 27
|
| 1889 |
-
},
|
| 1890 |
-
"Geometry": {
|
| 1891 |
-
"Average Score": 0.216402626,
|
| 1892 |
-
"Standard Deviation": 0.03338414918,
|
| 1893 |
-
"Rank": 39
|
| 1894 |
-
},
|
| 1895 |
-
"Algebra": {
|
| 1896 |
-
"Average Score": 0.233777838,
|
| 1897 |
-
"Standard Deviation": 0.0155226054,
|
| 1898 |
-
"Rank": 41
|
| 1899 |
-
},
|
| 1900 |
-
"Probability": {
|
| 1901 |
-
"Average Score": 0.25118175,
|
| 1902 |
-
"Standard Deviation": 0.04065514593,
|
| 1903 |
-
"Rank": 40
|
| 1904 |
-
},
|
| 1905 |
-
"Logical": {
|
| 1906 |
-
"Average Score": 0.224469136,
|
| 1907 |
-
"Standard Deviation": 0.03404706752,
|
| 1908 |
-
"Rank": 37
|
| 1909 |
-
},
|
| 1910 |
-
"Social": {
|
| 1911 |
-
"Average Score": 0.209386782,
|
| 1912 |
-
"Standard Deviation": 0.02738569921,
|
| 1913 |
-
"Rank": 39
|
| 1914 |
-
},
|
| 1915 |
-
"Chemistry": {
|
| 1916 |
-
"Average Score": 31.382959631870822,
|
| 1917 |
-
"Standard Deviation": null,
|
| 1918 |
-
"Rank": 35
|
| 1919 |
-
}
|
| 1920 |
-
}
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"config": {
|
| 1924 |
-
"model_name": "mistral-7b-instruct-1",
|
| 1925 |
-
"organization": "Mistral",
|
| 1926 |
-
"license": "Apache 2.0",
|
| 1927 |
-
"knowledge_cutoff": "2023/12"
|
| 1928 |
-
},
|
| 1929 |
-
"results": {
|
| 1930 |
-
"OVERALL": {
|
| 1931 |
-
"Average Score": 0.23016314,
|
| 1932 |
-
"Standard Deviation": 0.07137625271,
|
| 1933 |
-
"Rank": 46
|
| 1934 |
-
},
|
| 1935 |
-
"Geometry": {
|
| 1936 |
-
"Average Score": 0.161799938,
|
| 1937 |
-
"Standard Deviation": 0.03595278559,
|
| 1938 |
-
"Rank": 45
|
| 1939 |
-
},
|
| 1940 |
-
"Algebra": {
|
| 1941 |
-
"Average Score": 0.210341624,
|
| 1942 |
-
"Standard Deviation": 0.01736539119,
|
| 1943 |
-
"Rank": 42
|
| 1944 |
-
},
|
| 1945 |
-
"Probability": {
|
| 1946 |
-
"Average Score": 0.238417922,
|
| 1947 |
-
"Standard Deviation": 0.03744211933,
|
| 1948 |
-
"Rank": 41
|
| 1949 |
-
},
|
| 1950 |
-
"Logical": {
|
| 1951 |
-
"Average Score": 0.142636601,
|
| 1952 |
-
"Standard Deviation": 0.02080406365,
|
| 1953 |
-
"Rank": 46
|
| 1954 |
-
},
|
| 1955 |
-
"Social": {
|
| 1956 |
-
"Average Score": 0.117646827,
|
| 1957 |
-
"Standard Deviation": 0.009321202779,
|
| 1958 |
-
"Rank": 48
|
| 1959 |
-
},
|
| 1960 |
-
"Chemistry": {
|
| 1961 |
-
"Average Score": 18.929093202755805,
|
| 1962 |
-
"Standard Deviation": null,
|
| 1963 |
-
"Rank": 42
|
| 1964 |
-
}
|
| 1965 |
-
}
|
| 1966 |
-
},
|
| 1967 |
-
{
|
| 1968 |
-
"config": {
|
| 1969 |
-
"model_name": "vicuna-13b",
|
| 1970 |
-
"organization": "LMSYS",
|
| 1971 |
-
"license": "Non-commercial",
|
| 1972 |
-
"knowledge_cutoff": "2023/07"
|
| 1973 |
-
},
|
| 1974 |
-
"results": {
|
| 1975 |
-
"OVERALL": {
|
| 1976 |
-
"Average Score": 0.201892849,
|
| 1977 |
-
"Standard Deviation": 0.06021749802,
|
| 1978 |
-
"Rank": 47
|
| 1979 |
-
},
|
| 1980 |
-
"Geometry": {
|
| 1981 |
-
"Average Score": 0.200941928,
|
| 1982 |
-
"Standard Deviation": 0.03366817781,
|
| 1983 |
-
"Rank": 42
|
| 1984 |
-
},
|
| 1985 |
-
"Algebra": {
|
| 1986 |
-
"Average Score": 0.196123323,
|
| 1987 |
-
"Standard Deviation": 0.0135715643,
|
| 1988 |
-
"Rank": 43
|
| 1989 |
-
},
|
| 1990 |
-
"Probability": {
|
| 1991 |
-
"Average Score": 0.141214079,
|
| 1992 |
-
"Standard Deviation": 0.02721328211,
|
| 1993 |
-
"Rank": 45
|
| 1994 |
-
},
|
| 1995 |
-
"Logical": {
|
| 1996 |
-
"Average Score": 0.148598631,
|
| 1997 |
-
"Standard Deviation": 0.02241523892,
|
| 1998 |
-
"Rank": 44
|
| 1999 |
-
},
|
| 2000 |
-
"Social": {
|
| 2001 |
-
"Average Score": 0.124655135,
|
| 2002 |
-
"Standard Deviation": 0.01122382671,
|
| 2003 |
-
"Rank": 47
|
| 2004 |
-
},
|
| 2005 |
-
"Chemistry": {
|
| 2006 |
-
"Average Score": 21.840013221590294,
|
| 2007 |
-
"Standard Deviation": null,
|
| 2008 |
-
"Rank": 40
|
| 2009 |
-
}
|
| 2010 |
-
}
|
| 2011 |
-
},
|
| 2012 |
-
{
|
| 2013 |
-
"config": {
|
| 2014 |
-
"model_name": "zephyr-7b-beta",
|
| 2015 |
-
"organization": "HuggingFace",
|
| 2016 |
-
"license": "MIT",
|
| 2017 |
-
"knowledge_cutoff": "2023/10"
|
| 2018 |
-
},
|
| 2019 |
-
"results": {
|
| 2020 |
-
"OVERALL": {
|
| 2021 |
-
"Average Score": 0.102705119,
|
| 2022 |
-
"Standard Deviation": 0.03683757312,
|
| 2023 |
-
"Rank": 50
|
| 2024 |
-
},
|
| 2025 |
-
"Geometry": {
|
| 2026 |
-
"Average Score": 0.114005544,
|
| 2027 |
-
"Standard Deviation": 0.03144354365,
|
| 2028 |
-
"Rank": 46
|
| 2029 |
-
},
|
| 2030 |
-
"Algebra": {
|
| 2031 |
-
"Average Score": 0.141766633,
|
| 2032 |
-
"Standard Deviation": 0.03179520129,
|
| 2033 |
-
"Rank": 44
|
| 2034 |
-
},
|
| 2035 |
-
"Probability": {
|
| 2036 |
-
"Average Score": 0.089050714,
|
| 2037 |
-
"Standard Deviation": 0.002136754266,
|
| 2038 |
-
"Rank": 48
|
| 2039 |
-
},
|
| 2040 |
-
"Logical": {
|
| 2041 |
-
"Average Score": 0.069520789,
|
| 2042 |
-
"Standard Deviation": 0.004477840857,
|
| 2043 |
-
"Rank": 51
|
| 2044 |
-
},
|
| 2045 |
-
"Social": {
|
| 2046 |
-
"Average Score": 0.0,
|
| 2047 |
-
"Standard Deviation": 0.0,
|
| 2048 |
-
"Rank": 53
|
| 2049 |
-
},
|
| 2050 |
-
"Chemistry": {
|
| 2051 |
-
"Average Score": 18.92902220864132,
|
| 2052 |
-
"Standard Deviation": null,
|
| 2053 |
-
"Rank": 43
|
| 2054 |
-
}
|
| 2055 |
-
}
|
| 2056 |
-
},
|
| 2057 |
-
{
|
| 2058 |
-
"config": {
|
| 2059 |
-
"model_name": "gemma-1.1-2b-it",
|
| 2060 |
-
"organization": "Google",
|
| 2061 |
-
"license": "Gemma License",
|
| 2062 |
-
"knowledge_cutoff": "2024/02"
|
| 2063 |
-
},
|
| 2064 |
-
"results": {
|
| 2065 |
-
"OVERALL": {
|
| 2066 |
-
"Average Score": 0.257700845,
|
| 2067 |
-
"Standard Deviation": 0.07369021445,
|
| 2068 |
-
"Rank": 44
|
| 2069 |
-
},
|
| 2070 |
-
"Geometry": {
|
| 2071 |
-
"Average Score": 0.183974034,
|
| 2072 |
-
"Standard Deviation": 0.0215548886,
|
| 2073 |
-
"Rank": 44
|
| 2074 |
-
},
|
| 2075 |
-
"Algebra": {
|
| 2076 |
-
"Average Score": 0.13422252,
|
| 2077 |
-
"Standard Deviation": 0.01922819511,
|
| 2078 |
-
"Rank": 45
|
| 2079 |
-
},
|
| 2080 |
-
"Probability": {
|
| 2081 |
-
"Average Score": 0.095628657,
|
| 2082 |
-
"Standard Deviation": 0.007536076456,
|
| 2083 |
-
"Rank": 47
|
| 2084 |
-
},
|
| 2085 |
-
"Logical": {
|
| 2086 |
-
"Average Score": 0.094965074,
|
| 2087 |
-
"Standard Deviation": 0.005019175487,
|
| 2088 |
-
"Rank": 49
|
| 2089 |
-
},
|
| 2090 |
-
"Social": {
|
| 2091 |
-
"Average Score": 0.167796727,
|
| 2092 |
-
"Standard Deviation": 0.01666541942,
|
| 2093 |
-
"Rank": 43
|
| 2094 |
-
},
|
| 2095 |
-
"Chemistry": {
|
| 2096 |
-
"Average Score": 20.724691953843916,
|
| 2097 |
-
"Standard Deviation": null,
|
| 2098 |
-
"Rank": 41
|
| 2099 |
-
}
|
| 2100 |
-
}
|
| 2101 |
-
},
|
| 2102 |
-
{
|
| 2103 |
-
"config": {
|
| 2104 |
-
"model_name": "llama2-7b-chat",
|
| 2105 |
-
"organization": "Meta",
|
| 2106 |
-
"license": "Llama 2 Community",
|
| 2107 |
-
"knowledge_cutoff": "2023/07"
|
| 2108 |
-
},
|
| 2109 |
-
"results": {
|
| 2110 |
-
"OVERALL": {
|
| 2111 |
-
"Average Score": 0.260189428,
|
| 2112 |
-
"Standard Deviation": 0.08019299364,
|
| 2113 |
-
"Rank": 43
|
| 2114 |
-
},
|
| 2115 |
-
"Geometry": {
|
| 2116 |
-
"Average Score": 0.087067276,
|
| 2117 |
-
"Standard Deviation": 0.04274343402,
|
| 2118 |
-
"Rank": 47
|
| 2119 |
-
},
|
| 2120 |
-
"Algebra": {
|
| 2121 |
-
"Average Score": 0.12308805,
|
| 2122 |
-
"Standard Deviation": 0.01856053622,
|
| 2123 |
-
"Rank": 46
|
| 2124 |
-
},
|
| 2125 |
-
"Probability": {
|
| 2126 |
-
"Average Score": 0.087515438,
|
| 2127 |
-
"Standard Deviation": 0.006315053573,
|
| 2128 |
-
"Rank": 49
|
| 2129 |
-
},
|
| 2130 |
-
"Logical": {
|
| 2131 |
-
"Average Score": 0.17312827,
|
| 2132 |
-
"Standard Deviation": 0.01867044092,
|
| 2133 |
-
"Rank": 43
|
| 2134 |
-
},
|
| 2135 |
-
"Social": {
|
| 2136 |
-
"Average Score": 0.152905272,
|
| 2137 |
-
"Standard Deviation": 0.007166957097,
|
| 2138 |
-
"Rank": 44
|
| 2139 |
-
},
|
| 2140 |
-
"Chemistry": {
|
| 2141 |
-
"Average Score": 15.730513733660898,
|
| 2142 |
-
"Standard Deviation": null,
|
| 2143 |
-
"Rank": 45
|
| 2144 |
-
}
|
| 2145 |
-
}
|
| 2146 |
-
},
|
| 2147 |
-
{
|
| 2148 |
-
"config": {
|
| 2149 |
-
"model_name": "gemma-2b-it",
|
| 2150 |
-
"organization": "Google",
|
| 2151 |
-
"license": "Gemma License",
|
| 2152 |
-
"knowledge_cutoff": "2024/02"
|
| 2153 |
-
},
|
| 2154 |
-
"results": {
|
| 2155 |
-
"OVERALL": {
|
| 2156 |
-
"Average Score": 0.234172069,
|
| 2157 |
-
"Standard Deviation": 0.06522685718,
|
| 2158 |
-
"Rank": 45
|
| 2159 |
-
},
|
| 2160 |
-
"Geometry": {
|
| 2161 |
-
"Average Score": 0.198571153,
|
| 2162 |
-
"Standard Deviation": 0.01699161031,
|
| 2163 |
-
"Rank": 43
|
| 2164 |
-
},
|
| 2165 |
-
"Algebra": {
|
| 2166 |
-
"Average Score": 0.109883009,
|
| 2167 |
-
"Standard Deviation": 0.01520005833,
|
| 2168 |
-
"Rank": 47
|
| 2169 |
-
},
|
| 2170 |
-
"Probability": {
|
| 2171 |
-
"Average Score": 0.06467432,
|
| 2172 |
-
"Standard Deviation": 0.002117497231,
|
| 2173 |
-
"Rank": 51
|
| 2174 |
-
},
|
| 2175 |
-
"Logical": {
|
| 2176 |
-
"Average Score": 0.039624492,
|
| 2177 |
-
"Standard Deviation": 0.007606972686,
|
| 2178 |
-
"Rank": 52
|
| 2179 |
-
},
|
| 2180 |
-
"Social": {
|
| 2181 |
-
"Average Score": 0.087452913,
|
| 2182 |
-
"Standard Deviation": 0.008170146562,
|
| 2183 |
-
"Rank": 51
|
| 2184 |
-
},
|
| 2185 |
-
"Chemistry": {
|
| 2186 |
-
"Average Score": 17.2715657115764,
|
| 2187 |
-
"Standard Deviation": null,
|
| 2188 |
-
"Rank": 44
|
| 2189 |
-
}
|
| 2190 |
-
}
|
| 2191 |
-
},
|
| 2192 |
-
{
|
| 2193 |
-
"config": {
|
| 2194 |
-
"model_name": "llama2-13b-chat",
|
| 2195 |
-
"organization": "Meta",
|
| 2196 |
-
"license": "Llama 2 Community",
|
| 2197 |
-
"knowledge_cutoff": "2023/07"
|
| 2198 |
-
},
|
| 2199 |
-
"results": {
|
| 2200 |
-
"OVERALL": {
|
| 2201 |
-
"Average Score": 0.263305684,
|
| 2202 |
-
"Standard Deviation": 0.07283640689,
|
| 2203 |
-
"Rank": 42
|
| 2204 |
-
},
|
| 2205 |
-
"Geometry": {
|
| 2206 |
-
"Average Score": 0.072729954,
|
| 2207 |
-
"Standard Deviation": 0.02315988261,
|
| 2208 |
-
"Rank": 49
|
| 2209 |
-
},
|
| 2210 |
-
"Algebra": {
|
| 2211 |
-
"Average Score": 0.080371692,
|
| 2212 |
-
"Standard Deviation": 0.01277569453,
|
| 2213 |
-
"Rank": 48
|
| 2214 |
-
},
|
| 2215 |
-
"Probability": {
|
| 2216 |
-
"Average Score": 0.117757344,
|
| 2217 |
-
"Standard Deviation": 0.02418619619,
|
| 2218 |
-
"Rank": 46
|
| 2219 |
-
},
|
| 2220 |
-
"Logical": {
|
| 2221 |
-
"Average Score": 0.193149889,
|
| 2222 |
-
"Standard Deviation": 0.01776690764,
|
| 2223 |
-
"Rank": 40
|
| 2224 |
-
},
|
| 2225 |
-
"Social": {
|
| 2226 |
-
"Average Score": 0.149125922,
|
| 2227 |
-
"Standard Deviation": 0.01157416827,
|
| 2228 |
-
"Rank": 45
|
| 2229 |
-
},
|
| 2230 |
-
"Chemistry": {
|
| 2231 |
-
"Average Score": 13.17258252933903,
|
| 2232 |
-
"Standard Deviation": null,
|
| 2233 |
-
"Rank": 48
|
| 2234 |
-
}
|
| 2235 |
-
}
|
| 2236 |
-
},
|
| 2237 |
-
{
|
| 2238 |
-
"config": {
|
| 2239 |
-
"model_name": "vicuna-7b",
|
| 2240 |
-
"organization": "LMSYS",
|
| 2241 |
-
"license": "Non-commercial",
|
| 2242 |
-
"knowledge_cutoff": "2023/07"
|
| 2243 |
-
},
|
| 2244 |
-
"results": {
|
| 2245 |
-
"OVERALL": {
|
| 2246 |
-
"Average Score": 0.198839786,
|
| 2247 |
-
"Standard Deviation": 0.05725381576,
|
| 2248 |
-
"Rank": 48
|
| 2249 |
-
},
|
| 2250 |
-
"Geometry": {
|
| 2251 |
-
"Average Score": 0.083457058,
|
| 2252 |
-
"Standard Deviation": 0.02520989111,
|
| 2253 |
-
"Rank": 48
|
| 2254 |
-
},
|
| 2255 |
-
"Algebra": {
|
| 2256 |
-
"Average Score": 0.070883882,
|
| 2257 |
-
"Standard Deviation": 0.007315853253,
|
| 2258 |
-
"Rank": 49
|
| 2259 |
-
},
|
| 2260 |
-
"Probability": {
|
| 2261 |
-
"Average Score": 0.080987673,
|
| 2262 |
-
"Standard Deviation": 0.005474288861,
|
| 2263 |
-
"Rank": 50
|
| 2264 |
-
},
|
| 2265 |
-
"Logical": {
|
| 2266 |
-
"Average Score": 0.100065588,
|
| 2267 |
-
"Standard Deviation": 0.003561886452,
|
| 2268 |
-
"Rank": 48
|
| 2269 |
-
},
|
| 2270 |
-
"Social": {
|
| 2271 |
-
"Average Score": 0.111076414,
|
| 2272 |
-
"Standard Deviation": 0.004805626512,
|
| 2273 |
-
"Rank": 49
|
| 2274 |
-
},
|
| 2275 |
-
"Chemistry": {
|
| 2276 |
-
"Average Score": 14.255194156624162,
|
| 2277 |
-
"Standard Deviation": null,
|
| 2278 |
-
"Rank": 46
|
| 2279 |
-
}
|
| 2280 |
-
}
|
| 2281 |
-
},
|
| 2282 |
-
{
|
| 2283 |
-
"config": {
|
| 2284 |
-
"model_name": "koala-13b",
|
| 2285 |
-
"organization": "UC Berkeley",
|
| 2286 |
-
"license": "Non-commercial",
|
| 2287 |
-
"knowledge_cutoff": "2023/04"
|
| 2288 |
-
},
|
| 2289 |
-
"results": {
|
| 2290 |
-
"OVERALL": {
|
| 2291 |
-
"Average Score": 0.09387188,
|
| 2292 |
-
"Standard Deviation": 0.02642167489,
|
| 2293 |
-
"Rank": 51
|
| 2294 |
-
},
|
| 2295 |
-
"Geometry": {
|
| 2296 |
-
"Average Score": 0.017374001,
|
| 2297 |
-
"Standard Deviation": 0.01747053557,
|
| 2298 |
-
"Rank": 50
|
| 2299 |
-
},
|
| 2300 |
-
"Algebra": {
|
| 2301 |
-
"Average Score": 0.018129197,
|
| 2302 |
-
"Standard Deviation": 0.01054371383,
|
| 2303 |
-
"Rank": 50
|
| 2304 |
-
},
|
| 2305 |
-
"Probability": {
|
| 2306 |
-
"Average Score": 0.043654362,
|
| 2307 |
-
"Standard Deviation": 0.004288231886,
|
| 2308 |
-
"Rank": 52
|
| 2309 |
-
},
|
| 2310 |
-
"Logical": {
|
| 2311 |
-
"Average Score": 0.074694053,
|
| 2312 |
-
"Standard Deviation": 0.002674646998,
|
| 2313 |
-
"Rank": 50
|
| 2314 |
-
},
|
| 2315 |
-
"Social": {
|
| 2316 |
-
"Average Score": 0.096983835,
|
| 2317 |
-
"Standard Deviation": 0.007847059783,
|
| 2318 |
-
"Rank": 50
|
| 2319 |
-
},
|
| 2320 |
-
"Chemistry": {
|
| 2321 |
-
"Average Score": 6.36433272373514,
|
| 2322 |
-
"Standard Deviation": null,
|
| 2323 |
-
"Rank": 49
|
| 2324 |
-
}
|
| 2325 |
-
}
|
| 2326 |
-
},
|
| 2327 |
-
{
|
| 2328 |
-
"config": {
|
| 2329 |
-
"model_name": "openassistant-pythia-12b",
|
| 2330 |
-
"organization": "OpenAssistant",
|
| 2331 |
-
"license": "Non-commercial",
|
| 2332 |
-
"knowledge_cutoff": "2023/04"
|
| 2333 |
-
},
|
| 2334 |
-
"results": {
|
| 2335 |
-
"OVERALL": {
|
| 2336 |
-
"Average Score": 0.0,
|
| 2337 |
-
"Standard Deviation": 0.0,
|
| 2338 |
-
"Rank": 52
|
| 2339 |
-
},
|
| 2340 |
-
"Geometry": {
|
| 2341 |
-
"Average Score": 0.0,
|
| 2342 |
-
"Standard Deviation": 0.0,
|
| 2343 |
-
"Rank": 51
|
| 2344 |
-
},
|
| 2345 |
-
"Algebra": {
|
| 2346 |
-
"Average Score": 0.0,
|
| 2347 |
-
"Standard Deviation": 0.0,
|
| 2348 |
-
"Rank": 51
|
| 2349 |
-
},
|
| 2350 |
-
"Probability": {
|
| 2351 |
-
"Average Score": 0.0,
|
| 2352 |
-
"Standard Deviation": 0.0,
|
| 2353 |
-
"Rank": 53
|
| 2354 |
-
},
|
| 2355 |
-
"Logical": {
|
| 2356 |
-
"Average Score": 0.0,
|
| 2357 |
-
"Standard Deviation": 0.0,
|
| 2358 |
-
"Rank": 53
|
| 2359 |
-
},
|
| 2360 |
-
"Social": {
|
| 2361 |
-
"Average Score": 0.030792528,
|
| 2362 |
-
"Standard Deviation": 0.007518796391,
|
| 2363 |
-
"Rank": 52
|
| 2364 |
-
},
|
| 2365 |
-
"Chemistry": {
|
| 2366 |
-
"Average Score": 0.0,
|
| 2367 |
-
"Standard Deviation": null,
|
| 2368 |
-
"Rank": 50
|
| 2369 |
-
}
|
| 2370 |
-
}
|
| 2371 |
-
}
|
| 2372 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/models_2024-10-10-06:18:54.263527.json
DELETED
|
@@ -1,2622 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"config": {
|
| 4 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 5 |
-
"organization": "OpenAI",
|
| 6 |
-
"license": "Proprietary",
|
| 7 |
-
"knowledge_cutoff": "2023/10"
|
| 8 |
-
},
|
| 9 |
-
"results": {
|
| 10 |
-
"OVERALL": {
|
| 11 |
-
"Average Score": 0.974329609,
|
| 12 |
-
"Standard Deviation": 0.005024959031,
|
| 13 |
-
"Rank": 2
|
| 14 |
-
},
|
| 15 |
-
"Geometry": {
|
| 16 |
-
"Average Score": 0.976028578,
|
| 17 |
-
"Standard Deviation": 0.01507912373,
|
| 18 |
-
"Rank": 3
|
| 19 |
-
},
|
| 20 |
-
"Algebra": {
|
| 21 |
-
"Average Score": 0.951199453,
|
| 22 |
-
"Standard Deviation": 0.08452452108,
|
| 23 |
-
"Rank": 3
|
| 24 |
-
},
|
| 25 |
-
"Probability": {
|
| 26 |
-
"Average Score": 0.842116641,
|
| 27 |
-
"Standard Deviation": 0.006267759054,
|
| 28 |
-
"Rank": 3
|
| 29 |
-
},
|
| 30 |
-
"Logical": {
|
| 31 |
-
"Average Score": 0.828490728,
|
| 32 |
-
"Standard Deviation": 0.009134213144,
|
| 33 |
-
"Rank": 3
|
| 34 |
-
},
|
| 35 |
-
"Social": {
|
| 36 |
-
"Average Score": 0.815902987,
|
| 37 |
-
"Standard Deviation": 0.0196254222,
|
| 38 |
-
"Rank": 3
|
| 39 |
-
},
|
| 40 |
-
"Chemistry": {
|
| 41 |
-
"Average Score": 100.0,
|
| 42 |
-
"Standard Deviation": null,
|
| 43 |
-
"Rank": 1
|
| 44 |
-
},
|
| 45 |
-
"CPP": {
|
| 46 |
-
"Average Score": 100.0,
|
| 47 |
-
"Standard Deviation": null,
|
| 48 |
-
"Rank": 1
|
| 49 |
-
}
|
| 50 |
-
}
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"config": {
|
| 54 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 55 |
-
"organization": "OpenAI",
|
| 56 |
-
"license": "Proprietary",
|
| 57 |
-
"knowledge_cutoff": "2023/10"
|
| 58 |
-
},
|
| 59 |
-
"results": {
|
| 60 |
-
"OVERALL": {
|
| 61 |
-
"Average Score": 0.846571548,
|
| 62 |
-
"Standard Deviation": 0.03394056554,
|
| 63 |
-
"Rank": 6
|
| 64 |
-
},
|
| 65 |
-
"Geometry": {
|
| 66 |
-
"Average Score": 0.99773096,
|
| 67 |
-
"Standard Deviation": 0.002835555172,
|
| 68 |
-
"Rank": 1
|
| 69 |
-
},
|
| 70 |
-
"Algebra": {
|
| 71 |
-
"Average Score": 1.0,
|
| 72 |
-
"Standard Deviation": 0.0,
|
| 73 |
-
"Rank": 1
|
| 74 |
-
},
|
| 75 |
-
"Probability": {
|
| 76 |
-
"Average Score": 0.78855795,
|
| 77 |
-
"Standard Deviation": 0.008188675452,
|
| 78 |
-
"Rank": 6
|
| 79 |
-
},
|
| 80 |
-
"Logical": {
|
| 81 |
-
"Average Score": 0.668635768,
|
| 82 |
-
"Standard Deviation": 0.03466314094,
|
| 83 |
-
"Rank": 11
|
| 84 |
-
},
|
| 85 |
-
"Social": {
|
| 86 |
-
"Average Score": 0.680417314,
|
| 87 |
-
"Standard Deviation": 0.00656867063,
|
| 88 |
-
"Rank": 8
|
| 89 |
-
},
|
| 90 |
-
"Chemistry": {
|
| 91 |
-
"Average Score": 92.43090226400756,
|
| 92 |
-
"Standard Deviation": null,
|
| 93 |
-
"Rank": 2
|
| 94 |
-
},
|
| 95 |
-
"CPP": {
|
| 96 |
-
"Average Score": 92.43090226400756,
|
| 97 |
-
"Standard Deviation": null,
|
| 98 |
-
"Rank": 2
|
| 99 |
-
}
|
| 100 |
-
}
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"config": {
|
| 104 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 105 |
-
"organization": "OpenAI",
|
| 106 |
-
"license": "Proprietary",
|
| 107 |
-
"knowledge_cutoff": "2023/10"
|
| 108 |
-
},
|
| 109 |
-
"results": {
|
| 110 |
-
"OVERALL": {
|
| 111 |
-
"Average Score": 0.846334477,
|
| 112 |
-
"Standard Deviation": 0.09377911572,
|
| 113 |
-
"Rank": 7
|
| 114 |
-
},
|
| 115 |
-
"Geometry": {
|
| 116 |
-
"Average Score": 0.972472377,
|
| 117 |
-
"Standard Deviation": 0.01648274205,
|
| 118 |
-
"Rank": 4
|
| 119 |
-
},
|
| 120 |
-
"Algebra": {
|
| 121 |
-
"Average Score": 0.995511298,
|
| 122 |
-
"Standard Deviation": 0.004097802515,
|
| 123 |
-
"Rank": 2
|
| 124 |
-
},
|
| 125 |
-
"Probability": {
|
| 126 |
-
"Average Score": 0.812149974,
|
| 127 |
-
"Standard Deviation": 0.007669585485,
|
| 128 |
-
"Rank": 4
|
| 129 |
-
},
|
| 130 |
-
"Logical": {
|
| 131 |
-
"Average Score": 0.755019692,
|
| 132 |
-
"Standard Deviation": 0.008149588572,
|
| 133 |
-
"Rank": 6
|
| 134 |
-
},
|
| 135 |
-
"Social": {
|
| 136 |
-
"Average Score": 0.609875087,
|
| 137 |
-
"Standard Deviation": 0.038729239,
|
| 138 |
-
"Rank": 13
|
| 139 |
-
},
|
| 140 |
-
"Chemistry": {
|
| 141 |
-
"Average Score": 79.1592634699295,
|
| 142 |
-
"Standard Deviation": null,
|
| 143 |
-
"Rank": 5
|
| 144 |
-
},
|
| 145 |
-
"CPP": {
|
| 146 |
-
"Average Score": 79.1592634699295,
|
| 147 |
-
"Standard Deviation": null,
|
| 148 |
-
"Rank": 6
|
| 149 |
-
}
|
| 150 |
-
}
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"config": {
|
| 154 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 155 |
-
"organization": "OpenAI",
|
| 156 |
-
"license": "Proprietary",
|
| 157 |
-
"knowledge_cutoff": "2023/12"
|
| 158 |
-
},
|
| 159 |
-
"results": {
|
| 160 |
-
"OVERALL": {
|
| 161 |
-
"Average Score": 0.855357972,
|
| 162 |
-
"Standard Deviation": 0.1016986368,
|
| 163 |
-
"Rank": 4
|
| 164 |
-
},
|
| 165 |
-
"Geometry": {
|
| 166 |
-
"Average Score": 0.95374588,
|
| 167 |
-
"Standard Deviation": 0.03109307166,
|
| 168 |
-
"Rank": 5
|
| 169 |
-
},
|
| 170 |
-
"Algebra": {
|
| 171 |
-
"Average Score": 0.930945223,
|
| 172 |
-
"Standard Deviation": 0.06705136813,
|
| 173 |
-
"Rank": 4
|
| 174 |
-
},
|
| 175 |
-
"Probability": {
|
| 176 |
-
"Average Score": 0.750705448,
|
| 177 |
-
"Standard Deviation": 0.05944483103,
|
| 178 |
-
"Rank": 8
|
| 179 |
-
},
|
| 180 |
-
"Logical": {
|
| 181 |
-
"Average Score": 0.77906699,
|
| 182 |
-
"Standard Deviation": 0.007406734161,
|
| 183 |
-
"Rank": 4
|
| 184 |
-
},
|
| 185 |
-
"Social": {
|
| 186 |
-
"Average Score": 0.715935163,
|
| 187 |
-
"Standard Deviation": 0.1209141409,
|
| 188 |
-
"Rank": 6
|
| 189 |
-
},
|
| 190 |
-
"Chemistry": {
|
| 191 |
-
"Average Score": 70.73143363230263,
|
| 192 |
-
"Standard Deviation": null,
|
| 193 |
-
"Rank": 10
|
| 194 |
-
},
|
| 195 |
-
"CPP": {
|
| 196 |
-
"Average Score": 70.73143363230263,
|
| 197 |
-
"Standard Deviation": null,
|
| 198 |
-
"Rank": 11
|
| 199 |
-
}
|
| 200 |
-
}
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"config": {
|
| 204 |
-
"model_name": "gemini-1.5-pro-001",
|
| 205 |
-
"organization": "Google",
|
| 206 |
-
"license": "Proprietary",
|
| 207 |
-
"knowledge_cutoff": "2023/11"
|
| 208 |
-
},
|
| 209 |
-
"results": {
|
| 210 |
-
"OVERALL": {
|
| 211 |
-
"Average Score": 0.797187842,
|
| 212 |
-
"Standard Deviation": 0.0272375249,
|
| 213 |
-
"Rank": 10
|
| 214 |
-
},
|
| 215 |
-
"Geometry": {
|
| 216 |
-
"Average Score": 0.9947169,
|
| 217 |
-
"Standard Deviation": 0.009150597621,
|
| 218 |
-
"Rank": 2
|
| 219 |
-
},
|
| 220 |
-
"Algebra": {
|
| 221 |
-
"Average Score": 0.857464301,
|
| 222 |
-
"Standard Deviation": 0.05014285338,
|
| 223 |
-
"Rank": 5
|
| 224 |
-
},
|
| 225 |
-
"Probability": {
|
| 226 |
-
"Average Score": 0.651781767,
|
| 227 |
-
"Standard Deviation": 0.04156998547,
|
| 228 |
-
"Rank": 10
|
| 229 |
-
},
|
| 230 |
-
"Logical": {
|
| 231 |
-
"Average Score": 0.739745471,
|
| 232 |
-
"Standard Deviation": 0.01631532019,
|
| 233 |
-
"Rank": 7
|
| 234 |
-
},
|
| 235 |
-
"Social": {
|
| 236 |
-
"Average Score": 0.649601885,
|
| 237 |
-
"Standard Deviation": 0.104854889,
|
| 238 |
-
"Rank": 11
|
| 239 |
-
}
|
| 240 |
-
}
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"config": {
|
| 244 |
-
"model_name": "qwen2-72b-instruct",
|
| 245 |
-
"organization": "Alibaba",
|
| 246 |
-
"license": "Qianwen LICENSE",
|
| 247 |
-
"knowledge_cutoff": "2024/09"
|
| 248 |
-
},
|
| 249 |
-
"results": {
|
| 250 |
-
"OVERALL": {
|
| 251 |
-
"Average Score": 0.737918558,
|
| 252 |
-
"Standard Deviation": 0.09069077339,
|
| 253 |
-
"Rank": 11
|
| 254 |
-
},
|
| 255 |
-
"Geometry": {
|
| 256 |
-
"Average Score": 0.796870305,
|
| 257 |
-
"Standard Deviation": 0.0509025346,
|
| 258 |
-
"Rank": 9
|
| 259 |
-
},
|
| 260 |
-
"Algebra": {
|
| 261 |
-
"Average Score": 0.836194231,
|
| 262 |
-
"Standard Deviation": 0.04517093028,
|
| 263 |
-
"Rank": 6
|
| 264 |
-
},
|
| 265 |
-
"Probability": {
|
| 266 |
-
"Average Score": 0.788068004,
|
| 267 |
-
"Standard Deviation": 0.007288989044,
|
| 268 |
-
"Rank": 7
|
| 269 |
-
},
|
| 270 |
-
"Logical": {
|
| 271 |
-
"Average Score": 0.619300904,
|
| 272 |
-
"Standard Deviation": 0.06377931612,
|
| 273 |
-
"Rank": 14
|
| 274 |
-
},
|
| 275 |
-
"Social": {
|
| 276 |
-
"Average Score": 0.652578786,
|
| 277 |
-
"Standard Deviation": 0.04259293171,
|
| 278 |
-
"Rank": 10
|
| 279 |
-
},
|
| 280 |
-
"Chemistry": {
|
| 281 |
-
"Average Score": 73.54037778797029,
|
| 282 |
-
"Standard Deviation": null,
|
| 283 |
-
"Rank": 7
|
| 284 |
-
},
|
| 285 |
-
"CPP": {
|
| 286 |
-
"Average Score": 73.54037778797029,
|
| 287 |
-
"Standard Deviation": null,
|
| 288 |
-
"Rank": 7
|
| 289 |
-
}
|
| 290 |
-
}
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"config": {
|
| 294 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 295 |
-
"organization": "OpenAI",
|
| 296 |
-
"license": "Proprietary",
|
| 297 |
-
"knowledge_cutoff": "2023/10"
|
| 298 |
-
},
|
| 299 |
-
"results": {
|
| 300 |
-
"OVERALL": {
|
| 301 |
-
"Average Score": 0.847694133,
|
| 302 |
-
"Standard Deviation": 0.02164304402,
|
| 303 |
-
"Rank": 5
|
| 304 |
-
},
|
| 305 |
-
"Geometry": {
|
| 306 |
-
"Average Score": 0.946650435,
|
| 307 |
-
"Standard Deviation": 0.01831236482,
|
| 308 |
-
"Rank": 7
|
| 309 |
-
},
|
| 310 |
-
"Algebra": {
|
| 311 |
-
"Average Score": 0.796243022,
|
| 312 |
-
"Standard Deviation": 0.05537539202,
|
| 313 |
-
"Rank": 7
|
| 314 |
-
},
|
| 315 |
-
"Probability": {
|
| 316 |
-
"Average Score": 0.798402685,
|
| 317 |
-
"Standard Deviation": 0.009404491967,
|
| 318 |
-
"Rank": 5
|
| 319 |
-
},
|
| 320 |
-
"Logical": {
|
| 321 |
-
"Average Score": 0.727009735,
|
| 322 |
-
"Standard Deviation": 0.02628110141,
|
| 323 |
-
"Rank": 8
|
| 324 |
-
},
|
| 325 |
-
"Social": {
|
| 326 |
-
"Average Score": 0.691949855,
|
| 327 |
-
"Standard Deviation": 0.02072934333,
|
| 328 |
-
"Rank": 7
|
| 329 |
-
},
|
| 330 |
-
"Chemistry": {
|
| 331 |
-
"Average Score": 88.3877070580296,
|
| 332 |
-
"Standard Deviation": null,
|
| 333 |
-
"Rank": 3
|
| 334 |
-
},
|
| 335 |
-
"CPP": {
|
| 336 |
-
"Average Score": 88.3877070580296,
|
| 337 |
-
"Standard Deviation": null,
|
| 338 |
-
"Rank": 3
|
| 339 |
-
}
|
| 340 |
-
}
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"config": {
|
| 344 |
-
"model_name": "claude-3.5-sonnet",
|
| 345 |
-
"organization": "Anthropic",
|
| 346 |
-
"license": "Proprietary",
|
| 347 |
-
"knowledge_cutoff": "2024/04"
|
| 348 |
-
},
|
| 349 |
-
"results": {
|
| 350 |
-
"OVERALL": {
|
| 351 |
-
"Average Score": 0.839004422,
|
| 352 |
-
"Standard Deviation": 0.1461079564,
|
| 353 |
-
"Rank": 8
|
| 354 |
-
},
|
| 355 |
-
"Geometry": {
|
| 356 |
-
"Average Score": 0.95316419,
|
| 357 |
-
"Standard Deviation": 0.02081192856,
|
| 358 |
-
"Rank": 6
|
| 359 |
-
},
|
| 360 |
-
"Algebra": {
|
| 361 |
-
"Average Score": 0.759789952,
|
| 362 |
-
"Standard Deviation": 0.02611765096,
|
| 363 |
-
"Rank": 8
|
| 364 |
-
},
|
| 365 |
-
"Probability": {
|
| 366 |
-
"Average Score": 0.707730127,
|
| 367 |
-
"Standard Deviation": 0.0394436664,
|
| 368 |
-
"Rank": 9
|
| 369 |
-
},
|
| 370 |
-
"Logical": {
|
| 371 |
-
"Average Score": 0.77342666,
|
| 372 |
-
"Standard Deviation": 0.002892426458,
|
| 373 |
-
"Rank": 5
|
| 374 |
-
},
|
| 375 |
-
"Social": {
|
| 376 |
-
"Average Score": 0.790002247,
|
| 377 |
-
"Standard Deviation": 0.1007410022,
|
| 378 |
-
"Rank": 4
|
| 379 |
-
},
|
| 380 |
-
"Chemistry": {
|
| 381 |
-
"Average Score": 82.37734076815008,
|
| 382 |
-
"Standard Deviation": null,
|
| 383 |
-
"Rank": 4
|
| 384 |
-
},
|
| 385 |
-
"CPP": {
|
| 386 |
-
"Average Score": 82.37734076815008,
|
| 387 |
-
"Standard Deviation": null,
|
| 388 |
-
"Rank": 5
|
| 389 |
-
}
|
| 390 |
-
}
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"config": {
|
| 394 |
-
"model_name": "o1-mini",
|
| 395 |
-
"organization": "OpenAI",
|
| 396 |
-
"license": "Proprietary",
|
| 397 |
-
"knowledge_cutoff": "2023/10"
|
| 398 |
-
},
|
| 399 |
-
"results": {
|
| 400 |
-
"OVERALL": {
|
| 401 |
-
"Average Score": 1.0,
|
| 402 |
-
"Standard Deviation": 0.0,
|
| 403 |
-
"Rank": 1
|
| 404 |
-
},
|
| 405 |
-
"Geometry": {
|
| 406 |
-
"Average Score": "N/A",
|
| 407 |
-
"Standard Deviation": "N/A",
|
| 408 |
-
"Rank": "N/A"
|
| 409 |
-
},
|
| 410 |
-
"Algebra": {
|
| 411 |
-
"Average Score": "N/A",
|
| 412 |
-
"Standard Deviation": "N/A",
|
| 413 |
-
"Rank": "N/A"
|
| 414 |
-
},
|
| 415 |
-
"Probability": {
|
| 416 |
-
"Average Score": 1.0,
|
| 417 |
-
"Standard Deviation": 0.0,
|
| 418 |
-
"Rank": 1
|
| 419 |
-
},
|
| 420 |
-
"Logical": {
|
| 421 |
-
"Average Score": 1.0,
|
| 422 |
-
"Standard Deviation": 0.0,
|
| 423 |
-
"Rank": 1
|
| 424 |
-
},
|
| 425 |
-
"Social": {
|
| 426 |
-
"Average Score": 0.993974241,
|
| 427 |
-
"Standard Deviation": 0.001996882328,
|
| 428 |
-
"Rank": 2
|
| 429 |
-
}
|
| 430 |
-
}
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"config": {
|
| 434 |
-
"model_name": "o1-preview",
|
| 435 |
-
"organization": "OpenAI",
|
| 436 |
-
"license": "Proprietary",
|
| 437 |
-
"knowledge_cutoff": "2023/10"
|
| 438 |
-
},
|
| 439 |
-
"results": {
|
| 440 |
-
"OVERALL": {
|
| 441 |
-
"Average Score": 0.945884589,
|
| 442 |
-
"Standard Deviation": 0.01059250762,
|
| 443 |
-
"Rank": 3
|
| 444 |
-
},
|
| 445 |
-
"Geometry": {
|
| 446 |
-
"Average Score": "N/A",
|
| 447 |
-
"Standard Deviation": "N/A",
|
| 448 |
-
"Rank": "N/A"
|
| 449 |
-
},
|
| 450 |
-
"Algebra": {
|
| 451 |
-
"Average Score": "N/A",
|
| 452 |
-
"Standard Deviation": "N/A",
|
| 453 |
-
"Rank": "N/A"
|
| 454 |
-
},
|
| 455 |
-
"Probability": {
|
| 456 |
-
"Average Score": 0.964666392,
|
| 457 |
-
"Standard Deviation": 0.003139983398,
|
| 458 |
-
"Rank": 2
|
| 459 |
-
},
|
| 460 |
-
"Logical": {
|
| 461 |
-
"Average Score": 0.987950057,
|
| 462 |
-
"Standard Deviation": 0.004881220327,
|
| 463 |
-
"Rank": 2
|
| 464 |
-
},
|
| 465 |
-
"Social": {
|
| 466 |
-
"Average Score": 1.0,
|
| 467 |
-
"Standard Deviation": 0.0,
|
| 468 |
-
"Rank": 1
|
| 469 |
-
}
|
| 470 |
-
}
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"config": {
|
| 474 |
-
"model_name": "gemini-1.5-flash-001",
|
| 475 |
-
"organization": "Google",
|
| 476 |
-
"license": "Proprietary",
|
| 477 |
-
"knowledge_cutoff": "2023/11"
|
| 478 |
-
},
|
| 479 |
-
"results": {
|
| 480 |
-
"OVERALL": {
|
| 481 |
-
"Average Score": 0.726493401,
|
| 482 |
-
"Standard Deviation": 0.01113913725,
|
| 483 |
-
"Rank": 12
|
| 484 |
-
},
|
| 485 |
-
"Geometry": {
|
| 486 |
-
"Average Score": 0.804144103,
|
| 487 |
-
"Standard Deviation": 0.1327142178,
|
| 488 |
-
"Rank": 8
|
| 489 |
-
},
|
| 490 |
-
"Algebra": {
|
| 491 |
-
"Average Score": 0.731776765,
|
| 492 |
-
"Standard Deviation": 0.02594657111,
|
| 493 |
-
"Rank": 9
|
| 494 |
-
},
|
| 495 |
-
"Probability": {
|
| 496 |
-
"Average Score": 0.614461891,
|
| 497 |
-
"Standard Deviation": 0.04690131826,
|
| 498 |
-
"Rank": 13
|
| 499 |
-
},
|
| 500 |
-
"Logical": {
|
| 501 |
-
"Average Score": 0.630805991,
|
| 502 |
-
"Standard Deviation": 0.04871350612,
|
| 503 |
-
"Rank": 13
|
| 504 |
-
},
|
| 505 |
-
"Social": {
|
| 506 |
-
"Average Score": 0.555933822,
|
| 507 |
-
"Standard Deviation": 0.1029934524,
|
| 508 |
-
"Rank": 15
|
| 509 |
-
},
|
| 510 |
-
"Chemistry": {
|
| 511 |
-
"Average Score": 72.1127762005651,
|
| 512 |
-
"Standard Deviation": null,
|
| 513 |
-
"Rank": 9
|
| 514 |
-
},
|
| 515 |
-
"CPP": {
|
| 516 |
-
"Average Score": 72.1127762005651,
|
| 517 |
-
"Standard Deviation": null,
|
| 518 |
-
"Rank": 10
|
| 519 |
-
}
|
| 520 |
-
}
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"config": {
|
| 524 |
-
"model_name": "gpt4-1106",
|
| 525 |
-
"organization": "OpenAI",
|
| 526 |
-
"license": "Proprietary",
|
| 527 |
-
"knowledge_cutoff": "2024/04"
|
| 528 |
-
},
|
| 529 |
-
"results": {
|
| 530 |
-
"OVERALL": {
|
| 531 |
-
"Average Score": 0.816347784,
|
| 532 |
-
"Standard Deviation": 0.1566815755,
|
| 533 |
-
"Rank": 9
|
| 534 |
-
},
|
| 535 |
-
"Geometry": {
|
| 536 |
-
"Average Score": 0.71843088,
|
| 537 |
-
"Standard Deviation": 0.04778038294,
|
| 538 |
-
"Rank": 11
|
| 539 |
-
},
|
| 540 |
-
"Algebra": {
|
| 541 |
-
"Average Score": 0.712910417,
|
| 542 |
-
"Standard Deviation": 0.02581828898,
|
| 543 |
-
"Rank": 10
|
| 544 |
-
},
|
| 545 |
-
"Probability": {
|
| 546 |
-
"Average Score": 0.623947619,
|
| 547 |
-
"Standard Deviation": 0.03502982933,
|
| 548 |
-
"Rank": 12
|
| 549 |
-
},
|
| 550 |
-
"Logical": {
|
| 551 |
-
"Average Score": 0.637482274,
|
| 552 |
-
"Standard Deviation": 0.04158809888,
|
| 553 |
-
"Rank": 12
|
| 554 |
-
},
|
| 555 |
-
"Social": {
|
| 556 |
-
"Average Score": 0.450609816,
|
| 557 |
-
"Standard Deviation": 0.05208655446,
|
| 558 |
-
"Rank": 21
|
| 559 |
-
},
|
| 560 |
-
"Chemistry": {
|
| 561 |
-
"Average Score": 69.11824072252848,
|
| 562 |
-
"Standard Deviation": null,
|
| 563 |
-
"Rank": 11
|
| 564 |
-
},
|
| 565 |
-
"CPP": {
|
| 566 |
-
"Average Score": 69.11824072252848,
|
| 567 |
-
"Standard Deviation": null,
|
| 568 |
-
"Rank": 12
|
| 569 |
-
}
|
| 570 |
-
}
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"config": {
|
| 574 |
-
"model_name": "gemma-2-27b-it",
|
| 575 |
-
"organization": "Google",
|
| 576 |
-
"license": "Gemma License",
|
| 577 |
-
"knowledge_cutoff": "2024/06"
|
| 578 |
-
},
|
| 579 |
-
"results": {
|
| 580 |
-
"OVERALL": {
|
| 581 |
-
"Average Score": 0.624169623,
|
| 582 |
-
"Standard Deviation": 0.1048365121,
|
| 583 |
-
"Rank": 14
|
| 584 |
-
},
|
| 585 |
-
"Geometry": {
|
| 586 |
-
"Average Score": 0.60112744,
|
| 587 |
-
"Standard Deviation": 0.0469109952,
|
| 588 |
-
"Rank": 17
|
| 589 |
-
},
|
| 590 |
-
"Algebra": {
|
| 591 |
-
"Average Score": 0.687955914,
|
| 592 |
-
"Standard Deviation": 0.01959958192,
|
| 593 |
-
"Rank": 11
|
| 594 |
-
},
|
| 595 |
-
"Probability": {
|
| 596 |
-
"Average Score": 0.589524771,
|
| 597 |
-
"Standard Deviation": 0.03112689325,
|
| 598 |
-
"Rank": 14
|
| 599 |
-
},
|
| 600 |
-
"Logical": {
|
| 601 |
-
"Average Score": 0.614978944,
|
| 602 |
-
"Standard Deviation": 0.05710657859,
|
| 603 |
-
"Rank": 15
|
| 604 |
-
},
|
| 605 |
-
"Social": {
|
| 606 |
-
"Average Score": 0.487844257,
|
| 607 |
-
"Standard Deviation": 0.05857760809,
|
| 608 |
-
"Rank": 18
|
| 609 |
-
},
|
| 610 |
-
"Chemistry": {
|
| 611 |
-
"Average Score": 63.28920072143611,
|
| 612 |
-
"Standard Deviation": null,
|
| 613 |
-
"Rank": 13
|
| 614 |
-
},
|
| 615 |
-
"CPP": {
|
| 616 |
-
"Average Score": 63.28920072143611,
|
| 617 |
-
"Standard Deviation": null,
|
| 618 |
-
"Rank": 14
|
| 619 |
-
}
|
| 620 |
-
}
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"config": {
|
| 624 |
-
"model_name": "claude-3-opus",
|
| 625 |
-
"organization": "Anthropic",
|
| 626 |
-
"license": "Proprietary",
|
| 627 |
-
"knowledge_cutoff": "2023/08"
|
| 628 |
-
},
|
| 629 |
-
"results": {
|
| 630 |
-
"OVERALL": {
|
| 631 |
-
"Average Score": 0.650636271,
|
| 632 |
-
"Standard Deviation": 0.1197773541,
|
| 633 |
-
"Rank": 13
|
| 634 |
-
},
|
| 635 |
-
"Geometry": {
|
| 636 |
-
"Average Score": 0.7215743,
|
| 637 |
-
"Standard Deviation": 0.04712598358,
|
| 638 |
-
"Rank": 10
|
| 639 |
-
},
|
| 640 |
-
"Algebra": {
|
| 641 |
-
"Average Score": 0.68777327,
|
| 642 |
-
"Standard Deviation": 0.02382683713,
|
| 643 |
-
"Rank": 12
|
| 644 |
-
},
|
| 645 |
-
"Probability": {
|
| 646 |
-
"Average Score": 0.626471421,
|
| 647 |
-
"Standard Deviation": 0.02911817976,
|
| 648 |
-
"Rank": 11
|
| 649 |
-
},
|
| 650 |
-
"Logical": {
|
| 651 |
-
"Average Score": 0.692346381,
|
| 652 |
-
"Standard Deviation": 0.03617185198,
|
| 653 |
-
"Rank": 10
|
| 654 |
-
},
|
| 655 |
-
"Social": {
|
| 656 |
-
"Average Score": 0.663410854,
|
| 657 |
-
"Standard Deviation": 0.09540220876,
|
| 658 |
-
"Rank": 9
|
| 659 |
-
},
|
| 660 |
-
"Chemistry": {
|
| 661 |
-
"Average Score": 73.5404403567132,
|
| 662 |
-
"Standard Deviation": null,
|
| 663 |
-
"Rank": 6
|
| 664 |
-
},
|
| 665 |
-
"CPP": {
|
| 666 |
-
"Average Score": 73.5404403567132,
|
| 667 |
-
"Standard Deviation": null,
|
| 668 |
-
"Rank": 8
|
| 669 |
-
}
|
| 670 |
-
}
|
| 671 |
-
},
|
| 672 |
-
{
|
| 673 |
-
"config": {
|
| 674 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 675 |
-
"organization": "Google",
|
| 676 |
-
"license": "Gemma License",
|
| 677 |
-
"knowledge_cutoff": "2024/07"
|
| 678 |
-
},
|
| 679 |
-
"results": {
|
| 680 |
-
"OVERALL": {
|
| 681 |
-
"Average Score": "N/A",
|
| 682 |
-
"Standard Deviation": "N/A",
|
| 683 |
-
"Rank": "N/A"
|
| 684 |
-
},
|
| 685 |
-
"Geometry": {
|
| 686 |
-
"Average Score": 0.582787508,
|
| 687 |
-
"Standard Deviation": 0.03965204074,
|
| 688 |
-
"Rank": 18
|
| 689 |
-
},
|
| 690 |
-
"Algebra": {
|
| 691 |
-
"Average Score": 0.658648133,
|
| 692 |
-
"Standard Deviation": 0.02565919856,
|
| 693 |
-
"Rank": 13
|
| 694 |
-
},
|
| 695 |
-
"Probability": {
|
| 696 |
-
"Average Score": 0.547861265,
|
| 697 |
-
"Standard Deviation": 0.02885209131,
|
| 698 |
-
"Rank": 17
|
| 699 |
-
},
|
| 700 |
-
"Logical": {
|
| 701 |
-
"Average Score": 0.540720893,
|
| 702 |
-
"Standard Deviation": 0.01970134508,
|
| 703 |
-
"Rank": 19
|
| 704 |
-
},
|
| 705 |
-
"Social": {
|
| 706 |
-
"Average Score": 0.635266187,
|
| 707 |
-
"Standard Deviation": 0.03620021751,
|
| 708 |
-
"Rank": 12
|
| 709 |
-
},
|
| 710 |
-
"Chemistry": {
|
| 711 |
-
"Average Score": 73.43757596214863,
|
| 712 |
-
"Standard Deviation": null,
|
| 713 |
-
"Rank": 8
|
| 714 |
-
},
|
| 715 |
-
"CPP": {
|
| 716 |
-
"Average Score": 73.43757596214863,
|
| 717 |
-
"Standard Deviation": null,
|
| 718 |
-
"Rank": 9
|
| 719 |
-
}
|
| 720 |
-
}
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"config": {
|
| 724 |
-
"model_name": "qwen1.5-72b-chat",
|
| 725 |
-
"organization": "Alibaba",
|
| 726 |
-
"license": "Qianwen LICENSE",
|
| 727 |
-
"knowledge_cutoff": "2024/03"
|
| 728 |
-
},
|
| 729 |
-
"results": {
|
| 730 |
-
"OVERALL": {
|
| 731 |
-
"Average Score": 0.519549796,
|
| 732 |
-
"Standard Deviation": 0.00903634343,
|
| 733 |
-
"Rank": 17
|
| 734 |
-
},
|
| 735 |
-
"Geometry": {
|
| 736 |
-
"Average Score": 0.543139301,
|
| 737 |
-
"Standard Deviation": 0.03425202326,
|
| 738 |
-
"Rank": 22
|
| 739 |
-
},
|
| 740 |
-
"Algebra": {
|
| 741 |
-
"Average Score": 0.635228729,
|
| 742 |
-
"Standard Deviation": 0.01944043425,
|
| 743 |
-
"Rank": 14
|
| 744 |
-
},
|
| 745 |
-
"Probability": {
|
| 746 |
-
"Average Score": 0.486948658,
|
| 747 |
-
"Standard Deviation": 0.06064655315,
|
| 748 |
-
"Rank": 21
|
| 749 |
-
},
|
| 750 |
-
"Logical": {
|
| 751 |
-
"Average Score": 0.284069394,
|
| 752 |
-
"Standard Deviation": 0.02686608506,
|
| 753 |
-
"Rank": 32
|
| 754 |
-
},
|
| 755 |
-
"Social": {
|
| 756 |
-
"Average Score": 0.415007627,
|
| 757 |
-
"Standard Deviation": 0.03920053159,
|
| 758 |
-
"Rank": 22
|
| 759 |
-
},
|
| 760 |
-
"Chemistry": {
|
| 761 |
-
"Average Score": 48.69302376665551,
|
| 762 |
-
"Standard Deviation": null,
|
| 763 |
-
"Rank": 19
|
| 764 |
-
},
|
| 765 |
-
"CPP": {
|
| 766 |
-
"Average Score": 48.69302376665551,
|
| 767 |
-
"Standard Deviation": null,
|
| 768 |
-
"Rank": 20
|
| 769 |
-
}
|
| 770 |
-
}
|
| 771 |
-
},
|
| 772 |
-
{
|
| 773 |
-
"config": {
|
| 774 |
-
"model_name": "qwen1.5-32b-chat",
|
| 775 |
-
"organization": "Alibaba",
|
| 776 |
-
"license": "Qianwen LICENSE",
|
| 777 |
-
"knowledge_cutoff": "2024/03"
|
| 778 |
-
},
|
| 779 |
-
"results": {
|
| 780 |
-
"OVERALL": {
|
| 781 |
-
"Average Score": 0.393789407,
|
| 782 |
-
"Standard Deviation": 0.05413770095,
|
| 783 |
-
"Rank": 28
|
| 784 |
-
},
|
| 785 |
-
"Geometry": {
|
| 786 |
-
"Average Score": 0.51086835,
|
| 787 |
-
"Standard Deviation": 0.04052471998,
|
| 788 |
-
"Rank": 25
|
| 789 |
-
},
|
| 790 |
-
"Algebra": {
|
| 791 |
-
"Average Score": 0.609003168,
|
| 792 |
-
"Standard Deviation": 0.04874143541,
|
| 793 |
-
"Rank": 15
|
| 794 |
-
},
|
| 795 |
-
"Probability": {
|
| 796 |
-
"Average Score": 0.476300002,
|
| 797 |
-
"Standard Deviation": 0.05322403912,
|
| 798 |
-
"Rank": 22
|
| 799 |
-
},
|
| 800 |
-
"Logical": {
|
| 801 |
-
"Average Score": 0.331781014,
|
| 802 |
-
"Standard Deviation": 0.004938997686,
|
| 803 |
-
"Rank": 29
|
| 804 |
-
},
|
| 805 |
-
"Social": {
|
| 806 |
-
"Average Score": 0.380987334,
|
| 807 |
-
"Standard Deviation": 0.03762251776,
|
| 808 |
-
"Rank": 24
|
| 809 |
-
},
|
| 810 |
-
"Chemistry": {
|
| 811 |
-
"Average Score": 45.14284028264288,
|
| 812 |
-
"Standard Deviation": null,
|
| 813 |
-
"Rank": 23
|
| 814 |
-
},
|
| 815 |
-
"CPP": {
|
| 816 |
-
"Average Score": 45.14284028264288,
|
| 817 |
-
"Standard Deviation": null,
|
| 818 |
-
"Rank": 24
|
| 819 |
-
}
|
| 820 |
-
}
|
| 821 |
-
},
|
| 822 |
-
{
|
| 823 |
-
"config": {
|
| 824 |
-
"model_name": "google-gemma-2-9b-it",
|
| 825 |
-
"organization": "Google",
|
| 826 |
-
"license": "Proprietary",
|
| 827 |
-
"knowledge_cutoff": "2024/06"
|
| 828 |
-
},
|
| 829 |
-
"results": {
|
| 830 |
-
"OVERALL": {
|
| 831 |
-
"Average Score": 0.489663449,
|
| 832 |
-
"Standard Deviation": 0.002595702019,
|
| 833 |
-
"Rank": 20
|
| 834 |
-
},
|
| 835 |
-
"Geometry": {
|
| 836 |
-
"Average Score": 0.575371308,
|
| 837 |
-
"Standard Deviation": 0.03556220251,
|
| 838 |
-
"Rank": 20
|
| 839 |
-
},
|
| 840 |
-
"Algebra": {
|
| 841 |
-
"Average Score": 0.597045661,
|
| 842 |
-
"Standard Deviation": 0.0313828123,
|
| 843 |
-
"Rank": 16
|
| 844 |
-
},
|
| 845 |
-
"Probability": {
|
| 846 |
-
"Average Score": 0.589221807,
|
| 847 |
-
"Standard Deviation": 0.03110811656,
|
| 848 |
-
"Rank": 16
|
| 849 |
-
},
|
| 850 |
-
"Logical": {
|
| 851 |
-
"Average Score": 0.587579897,
|
| 852 |
-
"Standard Deviation": 0.05512716783,
|
| 853 |
-
"Rank": 17
|
| 854 |
-
},
|
| 855 |
-
"Social": {
|
| 856 |
-
"Average Score": 0.768337958,
|
| 857 |
-
"Standard Deviation": 0.04078610476,
|
| 858 |
-
"Rank": 5
|
| 859 |
-
},
|
| 860 |
-
"Chemistry": {
|
| 861 |
-
"Average Score": 54.03167523687635,
|
| 862 |
-
"Standard Deviation": null,
|
| 863 |
-
"Rank": 16
|
| 864 |
-
},
|
| 865 |
-
"CPP": {
|
| 866 |
-
"Average Score": 54.03167523687635,
|
| 867 |
-
"Standard Deviation": null,
|
| 868 |
-
"Rank": 17
|
| 869 |
-
}
|
| 870 |
-
}
|
| 871 |
-
},
|
| 872 |
-
{
|
| 873 |
-
"config": {
|
| 874 |
-
"model_name": "yi-1.5-34b-chat",
|
| 875 |
-
"organization": "01 AI",
|
| 876 |
-
"license": "Proprietary",
|
| 877 |
-
"knowledge_cutoff": "2024/05"
|
| 878 |
-
},
|
| 879 |
-
"results": {
|
| 880 |
-
"OVERALL": {
|
| 881 |
-
"Average Score": 0.607812897,
|
| 882 |
-
"Standard Deviation": 0.1440881293,
|
| 883 |
-
"Rank": 15
|
| 884 |
-
},
|
| 885 |
-
"Geometry": {
|
| 886 |
-
"Average Score": 0.566666724,
|
| 887 |
-
"Standard Deviation": 0.04001381658,
|
| 888 |
-
"Rank": 21
|
| 889 |
-
},
|
| 890 |
-
"Algebra": {
|
| 891 |
-
"Average Score": 0.590997292,
|
| 892 |
-
"Standard Deviation": 0.03594087315,
|
| 893 |
-
"Rank": 17
|
| 894 |
-
},
|
| 895 |
-
"Probability": {
|
| 896 |
-
"Average Score": 0.589524589,
|
| 897 |
-
"Standard Deviation": 0.03112618772,
|
| 898 |
-
"Rank": 15
|
| 899 |
-
},
|
| 900 |
-
"Logical": {
|
| 901 |
-
"Average Score": 0.574105508,
|
| 902 |
-
"Standard Deviation": 0.03441737941,
|
| 903 |
-
"Rank": 18
|
| 904 |
-
},
|
| 905 |
-
"Social": {
|
| 906 |
-
"Average Score": 0.516980832,
|
| 907 |
-
"Standard Deviation": 0.03369347985,
|
| 908 |
-
"Rank": 17
|
| 909 |
-
},
|
| 910 |
-
"Chemistry": {
|
| 911 |
-
"Average Score": 52.148798061768964,
|
| 912 |
-
"Standard Deviation": null,
|
| 913 |
-
"Rank": 17
|
| 914 |
-
},
|
| 915 |
-
"CPP": {
|
| 916 |
-
"Average Score": 52.148798061768964,
|
| 917 |
-
"Standard Deviation": null,
|
| 918 |
-
"Rank": 18
|
| 919 |
-
}
|
| 920 |
-
}
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"config": {
|
| 924 |
-
"model_name": "meta-llama-3.1-70b-instruct",
|
| 925 |
-
"organization": "Meta",
|
| 926 |
-
"license": "Llama 3.1 Community",
|
| 927 |
-
"knowledge_cutoff": "2023/12"
|
| 928 |
-
},
|
| 929 |
-
"results": {
|
| 930 |
-
"OVERALL": {
|
| 931 |
-
"Average Score": 0.708874896,
|
| 932 |
-
"Standard Deviation": 0.1315111956,
|
| 933 |
-
"Rank": 13
|
| 934 |
-
},
|
| 935 |
-
"Geometry": {
|
| 936 |
-
"Average Score": 0.76184398,
|
| 937 |
-
"Standard Deviation": 0.01790377984,
|
| 938 |
-
"Rank": 10
|
| 939 |
-
},
|
| 940 |
-
"Algebra": {
|
| 941 |
-
"Average Score": 0.732041699,
|
| 942 |
-
"Standard Deviation": 0.02621439062,
|
| 943 |
-
"Rank": 9
|
| 944 |
-
},
|
| 945 |
-
"Probability": {
|
| 946 |
-
"Average Score": 0.676208383,
|
| 947 |
-
"Standard Deviation": 0.05131201636,
|
| 948 |
-
"Rank": 10
|
| 949 |
-
},
|
| 950 |
-
"Logical": {
|
| 951 |
-
"Average Score": 0.620018631,
|
| 952 |
-
"Standard Deviation": 0.02518873821,
|
| 953 |
-
"Rank": 14
|
| 954 |
-
},
|
| 955 |
-
"Social": {
|
| 956 |
-
"Average Score": 0.45872939,
|
| 957 |
-
"Standard Deviation": 0.05347039576,
|
| 958 |
-
"Rank": 20
|
| 959 |
-
},
|
| 960 |
-
"Chemistry": {
|
| 961 |
-
"Average Score": 84.36815192532764,
|
| 962 |
-
"Standard Deviation": null,
|
| 963 |
-
"Rank": 4
|
| 964 |
-
},
|
| 965 |
-
"CPP": {
|
| 966 |
-
"Average Score": 84.36815192532764,
|
| 967 |
-
"Standard Deviation": null,
|
| 968 |
-
"Rank": 4
|
| 969 |
-
}
|
| 970 |
-
}
|
| 971 |
-
},
|
| 972 |
-
{
|
| 973 |
-
"config": {
|
| 974 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 975 |
-
"organization": "Meta",
|
| 976 |
-
"license": "Llama 3.1 Community",
|
| 977 |
-
"knowledge_cutoff": "2023/12"
|
| 978 |
-
},
|
| 979 |
-
"results": {
|
| 980 |
-
"OVERALL": {
|
| 981 |
-
"Average Score": 0.505936324,
|
| 982 |
-
"Standard Deviation": 0.05286756493,
|
| 983 |
-
"Rank": 18
|
| 984 |
-
},
|
| 985 |
-
"Geometry": {
|
| 986 |
-
"Average Score": 0.522442162,
|
| 987 |
-
"Standard Deviation": 0.03908236317,
|
| 988 |
-
"Rank": 23
|
| 989 |
-
},
|
| 990 |
-
"Algebra": {
|
| 991 |
-
"Average Score": 0.582702645,
|
| 992 |
-
"Standard Deviation": 0.05002277711,
|
| 993 |
-
"Rank": 18
|
| 994 |
-
},
|
| 995 |
-
"Probability": {
|
| 996 |
-
"Average Score": 0.495001149,
|
| 997 |
-
"Standard Deviation": 0.05244587037,
|
| 998 |
-
"Rank": 20
|
| 999 |
-
},
|
| 1000 |
-
"Logical": {
|
| 1001 |
-
"Average Score": 0.443030561,
|
| 1002 |
-
"Standard Deviation": 0.01343820628,
|
| 1003 |
-
"Rank": 24
|
| 1004 |
-
},
|
| 1005 |
-
"Social": {
|
| 1006 |
-
"Average Score": 0.329195941,
|
| 1007 |
-
"Standard Deviation": 0.03925019528,
|
| 1008 |
-
"Rank": 28
|
| 1009 |
-
},
|
| 1010 |
-
"Chemistry": {
|
| 1011 |
-
"Average Score": 44.41846841004584,
|
| 1012 |
-
"Standard Deviation": null,
|
| 1013 |
-
"Rank": 25
|
| 1014 |
-
},
|
| 1015 |
-
"CPP": {
|
| 1016 |
-
"Average Score": 44.41846841004584,
|
| 1017 |
-
"Standard Deviation": null,
|
| 1018 |
-
"Rank": 26
|
| 1019 |
-
}
|
| 1020 |
-
}
|
| 1021 |
-
},
|
| 1022 |
-
{
|
| 1023 |
-
"config": {
|
| 1024 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 1025 |
-
"organization": "OpenAI",
|
| 1026 |
-
"license": "Proprietary",
|
| 1027 |
-
"knowledge_cutoff": "2021/09"
|
| 1028 |
-
},
|
| 1029 |
-
"results": {
|
| 1030 |
-
"OVERALL": {
|
| 1031 |
-
"Average Score": 0.313398088,
|
| 1032 |
-
"Standard Deviation": 0.09322528606,
|
| 1033 |
-
"Rank": 39
|
| 1034 |
-
},
|
| 1035 |
-
"Geometry": {
|
| 1036 |
-
"Average Score": 0.678714519,
|
| 1037 |
-
"Standard Deviation": 0.05926546762,
|
| 1038 |
-
"Rank": 12
|
| 1039 |
-
},
|
| 1040 |
-
"Algebra": {
|
| 1041 |
-
"Average Score": 0.569296173,
|
| 1042 |
-
"Standard Deviation": 0.05277281097,
|
| 1043 |
-
"Rank": 19
|
| 1044 |
-
},
|
| 1045 |
-
"Probability": {
|
| 1046 |
-
"Average Score": 0.448460767,
|
| 1047 |
-
"Standard Deviation": 0.05768095196,
|
| 1048 |
-
"Rank": 24
|
| 1049 |
-
},
|
| 1050 |
-
"Logical": {
|
| 1051 |
-
"Average Score": 0.148521348,
|
| 1052 |
-
"Standard Deviation": 0.04033712907,
|
| 1053 |
-
"Rank": 44
|
| 1054 |
-
},
|
| 1055 |
-
"Social": {
|
| 1056 |
-
"Average Score": 0.235071541,
|
| 1057 |
-
"Standard Deviation": 0.02632892457,
|
| 1058 |
-
"Rank": 37
|
| 1059 |
-
},
|
| 1060 |
-
"Chemistry": {
|
| 1061 |
-
"Average Score": 40.46958736582551,
|
| 1062 |
-
"Standard Deviation": null,
|
| 1063 |
-
"Rank": 28
|
| 1064 |
-
},
|
| 1065 |
-
"CPP": {
|
| 1066 |
-
"Average Score": 40.46958736582551,
|
| 1067 |
-
"Standard Deviation": null,
|
| 1068 |
-
"Rank": 29
|
| 1069 |
-
}
|
| 1070 |
-
}
|
| 1071 |
-
},
|
| 1072 |
-
{
|
| 1073 |
-
"config": {
|
| 1074 |
-
"model_name": "llama-3-70b-instruct",
|
| 1075 |
-
"organization": "Meta",
|
| 1076 |
-
"license": "Llama 3 Community",
|
| 1077 |
-
"knowledge_cutoff": "2023/12"
|
| 1078 |
-
},
|
| 1079 |
-
"results": {
|
| 1080 |
-
"OVERALL": {
|
| 1081 |
-
"Average Score": 0.456689885,
|
| 1082 |
-
"Standard Deviation": 0.01385989995,
|
| 1083 |
-
"Rank": 22
|
| 1084 |
-
},
|
| 1085 |
-
"Geometry": {
|
| 1086 |
-
"Average Score": 0.516865529,
|
| 1087 |
-
"Standard Deviation": 0.03858112564,
|
| 1088 |
-
"Rank": 24
|
| 1089 |
-
},
|
| 1090 |
-
"Algebra": {
|
| 1091 |
-
"Average Score": 0.566756531,
|
| 1092 |
-
"Standard Deviation": 0.03369826926,
|
| 1093 |
-
"Rank": 20
|
| 1094 |
-
},
|
| 1095 |
-
"Probability": {
|
| 1096 |
-
"Average Score": 0.513857306,
|
| 1097 |
-
"Standard Deviation": 0.05453699062,
|
| 1098 |
-
"Rank": 19
|
| 1099 |
-
},
|
| 1100 |
-
"Logical": {
|
| 1101 |
-
"Average Score": 0.713796415,
|
| 1102 |
-
"Standard Deviation": 0.02031215107,
|
| 1103 |
-
"Rank": 9
|
| 1104 |
-
},
|
| 1105 |
-
"Social": {
|
| 1106 |
-
"Average Score": 0.45872939,
|
| 1107 |
-
"Standard Deviation": 0.05347039576,
|
| 1108 |
-
"Rank": 20
|
| 1109 |
-
},
|
| 1110 |
-
"Chemistry": {
|
| 1111 |
-
"Average Score": 65.32140697218945,
|
| 1112 |
-
"Standard Deviation": null,
|
| 1113 |
-
"Rank": 12
|
| 1114 |
-
},
|
| 1115 |
-
"CPP": {
|
| 1116 |
-
"Average Score": 65.32140697218945,
|
| 1117 |
-
"Standard Deviation": null,
|
| 1118 |
-
"Rank": 13
|
| 1119 |
-
}
|
| 1120 |
-
}
|
| 1121 |
-
},
|
| 1122 |
-
{
|
| 1123 |
-
"config": {
|
| 1124 |
-
"model_name": "claude-3-sonnet",
|
| 1125 |
-
"organization": "Anthropic",
|
| 1126 |
-
"license": "Proprietary",
|
| 1127 |
-
"knowledge_cutoff": "2023/08"
|
| 1128 |
-
},
|
| 1129 |
-
"results": {
|
| 1130 |
-
"OVERALL": {
|
| 1131 |
-
"Average Score": 0.520010833,
|
| 1132 |
-
"Standard Deviation": 0.005030563799,
|
| 1133 |
-
"Rank": 16
|
| 1134 |
-
},
|
| 1135 |
-
"Geometry": {
|
| 1136 |
-
"Average Score": 0.675613638,
|
| 1137 |
-
"Standard Deviation": 0.05275594408,
|
| 1138 |
-
"Rank": 13
|
| 1139 |
-
},
|
| 1140 |
-
"Algebra": {
|
| 1141 |
-
"Average Score": 0.552025728,
|
| 1142 |
-
"Standard Deviation": 0.04122192409,
|
| 1143 |
-
"Rank": 21
|
| 1144 |
-
},
|
| 1145 |
-
"Probability": {
|
| 1146 |
-
"Average Score": 0.516192848,
|
| 1147 |
-
"Standard Deviation": 0.04152293217,
|
| 1148 |
-
"Rank": 18
|
| 1149 |
-
},
|
| 1150 |
-
"Logical": {
|
| 1151 |
-
"Average Score": 0.588545747,
|
| 1152 |
-
"Standard Deviation": 0.06068211943,
|
| 1153 |
-
"Rank": 16
|
| 1154 |
-
},
|
| 1155 |
-
"Social": {
|
| 1156 |
-
"Average Score": 0.570437582,
|
| 1157 |
-
"Standard Deviation": 0.08607040862,
|
| 1158 |
-
"Rank": 14
|
| 1159 |
-
},
|
| 1160 |
-
"Chemistry": {
|
| 1161 |
-
"Average Score": 61.33538592327427,
|
| 1162 |
-
"Standard Deviation": null,
|
| 1163 |
-
"Rank": 14
|
| 1164 |
-
},
|
| 1165 |
-
"CPP": {
|
| 1166 |
-
"Average Score": 61.33538592327427,
|
| 1167 |
-
"Standard Deviation": null,
|
| 1168 |
-
"Rank": 15
|
| 1169 |
-
}
|
| 1170 |
-
}
|
| 1171 |
-
},
|
| 1172 |
-
{
|
| 1173 |
-
"config": {
|
| 1174 |
-
"model_name": "qwen1.5-14b-chat",
|
| 1175 |
-
"organization": "Alibaba",
|
| 1176 |
-
"license": "Qianwen LICENSE",
|
| 1177 |
-
"knowledge_cutoff": "2024/02"
|
| 1178 |
-
},
|
| 1179 |
-
"results": {
|
| 1180 |
-
"OVERALL": {
|
| 1181 |
-
"Average Score": 0.415328996,
|
| 1182 |
-
"Standard Deviation": 0.0743938717,
|
| 1183 |
-
"Rank": 27
|
| 1184 |
-
},
|
| 1185 |
-
"Geometry": {
|
| 1186 |
-
"Average Score": 0.452504016,
|
| 1187 |
-
"Standard Deviation": 0.04225594393,
|
| 1188 |
-
"Rank": 26
|
| 1189 |
-
},
|
| 1190 |
-
"Algebra": {
|
| 1191 |
-
"Average Score": 0.538655725,
|
| 1192 |
-
"Standard Deviation": 0.03721542594,
|
| 1193 |
-
"Rank": 22
|
| 1194 |
-
},
|
| 1195 |
-
"Probability": {
|
| 1196 |
-
"Average Score": 0.397185975,
|
| 1197 |
-
"Standard Deviation": 0.05607695946,
|
| 1198 |
-
"Rank": 28
|
| 1199 |
-
},
|
| 1200 |
-
"Logical": {
|
| 1201 |
-
"Average Score": 0.264573129,
|
| 1202 |
-
"Standard Deviation": 0.03936133174,
|
| 1203 |
-
"Rank": 34
|
| 1204 |
-
},
|
| 1205 |
-
"Social": {
|
| 1206 |
-
"Average Score": 0.287370142,
|
| 1207 |
-
"Standard Deviation": 0.04264085315,
|
| 1208 |
-
"Rank": 30
|
| 1209 |
-
},
|
| 1210 |
-
"Chemistry": {
|
| 1211 |
-
"Average Score": 38.552779976347026,
|
| 1212 |
-
"Standard Deviation": null,
|
| 1213 |
-
"Rank": 30
|
| 1214 |
-
},
|
| 1215 |
-
"CPP": {
|
| 1216 |
-
"Average Score": 38.552779976347026,
|
| 1217 |
-
"Standard Deviation": null,
|
| 1218 |
-
"Rank": 31
|
| 1219 |
-
}
|
| 1220 |
-
}
|
| 1221 |
-
},
|
| 1222 |
-
{
|
| 1223 |
-
"config": {
|
| 1224 |
-
"model_name": "claude-3-haiku",
|
| 1225 |
-
"organization": "Anthropic",
|
| 1226 |
-
"license": "Proprietary",
|
| 1227 |
-
"knowledge_cutoff": "2023/08"
|
| 1228 |
-
},
|
| 1229 |
-
"results": {
|
| 1230 |
-
"OVERALL": {
|
| 1231 |
-
"Average Score": 0.453901163,
|
| 1232 |
-
"Standard Deviation": 0.003604084261,
|
| 1233 |
-
"Rank": 23
|
| 1234 |
-
},
|
| 1235 |
-
"Geometry": {
|
| 1236 |
-
"Average Score": 0.607993912,
|
| 1237 |
-
"Standard Deviation": 0.05793460748,
|
| 1238 |
-
"Rank": 15
|
| 1239 |
-
},
|
| 1240 |
-
"Algebra": {
|
| 1241 |
-
"Average Score": 0.520054055,
|
| 1242 |
-
"Standard Deviation": 0.03333544511,
|
| 1243 |
-
"Rank": 23
|
| 1244 |
-
},
|
| 1245 |
-
"Probability": {
|
| 1246 |
-
"Average Score": 0.474460688,
|
| 1247 |
-
"Standard Deviation": 0.0446501933,
|
| 1248 |
-
"Rank": 23
|
| 1249 |
-
},
|
| 1250 |
-
"Logical": {
|
| 1251 |
-
"Average Score": 0.512815976,
|
| 1252 |
-
"Standard Deviation": 0.0163264281,
|
| 1253 |
-
"Rank": 20
|
| 1254 |
-
},
|
| 1255 |
-
"Social": {
|
| 1256 |
-
"Average Score": 0.551083976,
|
| 1257 |
-
"Standard Deviation": 0.05374722539,
|
| 1258 |
-
"Rank": 16
|
| 1259 |
-
},
|
| 1260 |
-
"Chemistry": {
|
| 1261 |
-
"Average Score": 56.40200048817984,
|
| 1262 |
-
"Standard Deviation": null,
|
| 1263 |
-
"Rank": 15
|
| 1264 |
-
},
|
| 1265 |
-
"CPP": {
|
| 1266 |
-
"Average Score": 56.40200048817984,
|
| 1267 |
-
"Standard Deviation": null,
|
| 1268 |
-
"Rank": 16
|
| 1269 |
-
}
|
| 1270 |
-
}
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"config": {
|
| 1274 |
-
"model_name": "claude-2.1",
|
| 1275 |
-
"organization": "Anthropic",
|
| 1276 |
-
"license": "Proprietary",
|
| 1277 |
-
"knowledge_cutoff": "Unknown"
|
| 1278 |
-
},
|
| 1279 |
-
"results": {
|
| 1280 |
-
"OVERALL": {
|
| 1281 |
-
"Average Score": 0.35814708,
|
| 1282 |
-
"Standard Deviation": 0.09168134168,
|
| 1283 |
-
"Rank": 35
|
| 1284 |
-
},
|
| 1285 |
-
"Geometry": {
|
| 1286 |
-
"Average Score": 0.62752395,
|
| 1287 |
-
"Standard Deviation": 0.07232659398,
|
| 1288 |
-
"Rank": 14
|
| 1289 |
-
},
|
| 1290 |
-
"Algebra": {
|
| 1291 |
-
"Average Score": 0.508849609,
|
| 1292 |
-
"Standard Deviation": 0.0346897465,
|
| 1293 |
-
"Rank": 24
|
| 1294 |
-
},
|
| 1295 |
-
"Probability": {
|
| 1296 |
-
"Average Score": 0.41477086,
|
| 1297 |
-
"Standard Deviation": 0.05964060239,
|
| 1298 |
-
"Rank": 27
|
| 1299 |
-
},
|
| 1300 |
-
"Logical": {
|
| 1301 |
-
"Average Score": 0.482923674,
|
| 1302 |
-
"Standard Deviation": 0.01989147048,
|
| 1303 |
-
"Rank": 21
|
| 1304 |
-
},
|
| 1305 |
-
"Social": {
|
| 1306 |
-
"Average Score": 0.333804568,
|
| 1307 |
-
"Standard Deviation": 0.03775548253,
|
| 1308 |
-
"Rank": 27
|
| 1309 |
-
},
|
| 1310 |
-
"Chemistry": {
|
| 1311 |
-
"Average Score": 47.23672563994903,
|
| 1312 |
-
"Standard Deviation": null,
|
| 1313 |
-
"Rank": 20
|
| 1314 |
-
},
|
| 1315 |
-
"CPP": {
|
| 1316 |
-
"Average Score": 47.23672563994903,
|
| 1317 |
-
"Standard Deviation": null,
|
| 1318 |
-
"Rank": 21
|
| 1319 |
-
}
|
| 1320 |
-
}
|
| 1321 |
-
},
|
| 1322 |
-
{
|
| 1323 |
-
"config": {
|
| 1324 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 1325 |
-
"organization": "Mistral",
|
| 1326 |
-
"license": "Apache 2.0",
|
| 1327 |
-
"knowledge_cutoff": "2023/12"
|
| 1328 |
-
},
|
| 1329 |
-
"results": {
|
| 1330 |
-
"OVERALL": {
|
| 1331 |
-
"Average Score": 0.382659161,
|
| 1332 |
-
"Standard Deviation": 0.07594496929,
|
| 1333 |
-
"Rank": 30
|
| 1334 |
-
},
|
| 1335 |
-
"Geometry": {
|
| 1336 |
-
"Average Score": 0.432216097,
|
| 1337 |
-
"Standard Deviation": 0.04747949254,
|
| 1338 |
-
"Rank": 29
|
| 1339 |
-
},
|
| 1340 |
-
"Algebra": {
|
| 1341 |
-
"Average Score": 0.478314888,
|
| 1342 |
-
"Standard Deviation": 0.01998797419,
|
| 1343 |
-
"Rank": 25
|
| 1344 |
-
},
|
| 1345 |
-
"Probability": {
|
| 1346 |
-
"Average Score": 0.427144725,
|
| 1347 |
-
"Standard Deviation": 0.0590923329,
|
| 1348 |
-
"Rank": 26
|
| 1349 |
-
},
|
| 1350 |
-
"Logical": {
|
| 1351 |
-
"Average Score": 0.340041983,
|
| 1352 |
-
"Standard Deviation": 0.008397574592,
|
| 1353 |
-
"Rank": 27
|
| 1354 |
-
},
|
| 1355 |
-
"Social": {
|
| 1356 |
-
"Average Score": 0.251949622,
|
| 1357 |
-
"Standard Deviation": 0.03346674405,
|
| 1358 |
-
"Rank": 35
|
| 1359 |
-
},
|
| 1360 |
-
"Chemistry": {
|
| 1361 |
-
"Average Score": 44.533118241976666,
|
| 1362 |
-
"Standard Deviation": null,
|
| 1363 |
-
"Rank": 24
|
| 1364 |
-
},
|
| 1365 |
-
"CPP": {
|
| 1366 |
-
"Average Score": 44.533118241976666,
|
| 1367 |
-
"Standard Deviation": null,
|
| 1368 |
-
"Rank": 25
|
| 1369 |
-
}
|
| 1370 |
-
}
|
| 1371 |
-
},
|
| 1372 |
-
{
|
| 1373 |
-
"config": {
|
| 1374 |
-
"model_name": "claude-2.0",
|
| 1375 |
-
"organization": "Anthropic",
|
| 1376 |
-
"license": "Proprietary",
|
| 1377 |
-
"knowledge_cutoff": "Unknown"
|
| 1378 |
-
},
|
| 1379 |
-
"results": {
|
| 1380 |
-
"OVERALL": {
|
| 1381 |
-
"Average Score": 0.322718057,
|
| 1382 |
-
"Standard Deviation": 0.08369883584,
|
| 1383 |
-
"Rank": 37
|
| 1384 |
-
},
|
| 1385 |
-
"Geometry": {
|
| 1386 |
-
"Average Score": 0.604141967,
|
| 1387 |
-
"Standard Deviation": 0.05116441826,
|
| 1388 |
-
"Rank": 16
|
| 1389 |
-
},
|
| 1390 |
-
"Algebra": {
|
| 1391 |
-
"Average Score": 0.474350734,
|
| 1392 |
-
"Standard Deviation": 0.01510393066,
|
| 1393 |
-
"Rank": 26
|
| 1394 |
-
},
|
| 1395 |
-
"Probability": {
|
| 1396 |
-
"Average Score": 0.437950412,
|
| 1397 |
-
"Standard Deviation": 0.05985594317,
|
| 1398 |
-
"Rank": 25
|
| 1399 |
-
},
|
| 1400 |
-
"Logical": {
|
| 1401 |
-
"Average Score": 0.445620646,
|
| 1402 |
-
"Standard Deviation": 0.01812614805,
|
| 1403 |
-
"Rank": 23
|
| 1404 |
-
},
|
| 1405 |
-
"Social": {
|
| 1406 |
-
"Average Score": 0.469422836,
|
| 1407 |
-
"Standard Deviation": 0.05999901796,
|
| 1408 |
-
"Rank": 19
|
| 1409 |
-
},
|
| 1410 |
-
"Chemistry": {
|
| 1411 |
-
"Average Score": 50.773143448036464,
|
| 1412 |
-
"Standard Deviation": null,
|
| 1413 |
-
"Rank": 18
|
| 1414 |
-
},
|
| 1415 |
-
"CPP": {
|
| 1416 |
-
"Average Score": 50.773143448036464,
|
| 1417 |
-
"Standard Deviation": null,
|
| 1418 |
-
"Rank": 19
|
| 1419 |
-
}
|
| 1420 |
-
}
|
| 1421 |
-
},
|
| 1422 |
-
{
|
| 1423 |
-
"config": {
|
| 1424 |
-
"model_name": "starling-lm-7b-beta",
|
| 1425 |
-
"organization": "Nexusflow",
|
| 1426 |
-
"license": "Apache-2.0",
|
| 1427 |
-
"knowledge_cutoff": "2024/03"
|
| 1428 |
-
},
|
| 1429 |
-
"results": {
|
| 1430 |
-
"OVERALL": {
|
| 1431 |
-
"Average Score": 0.479391856,
|
| 1432 |
-
"Standard Deviation": 0.04199990887,
|
| 1433 |
-
"Rank": 21
|
| 1434 |
-
},
|
| 1435 |
-
"Geometry": {
|
| 1436 |
-
"Average Score": 0.446654388,
|
| 1437 |
-
"Standard Deviation": 0.05637864999,
|
| 1438 |
-
"Rank": 28
|
| 1439 |
-
},
|
| 1440 |
-
"Algebra": {
|
| 1441 |
-
"Average Score": 0.473952749,
|
| 1442 |
-
"Standard Deviation": 0.01584301288,
|
| 1443 |
-
"Rank": 27
|
| 1444 |
-
},
|
| 1445 |
-
"Probability": {
|
| 1446 |
-
"Average Score": 0.395197837,
|
| 1447 |
-
"Standard Deviation": 0.05814798892,
|
| 1448 |
-
"Rank": 29
|
| 1449 |
-
},
|
| 1450 |
-
"Logical": {
|
| 1451 |
-
"Average Score": 0.39927199,
|
| 1452 |
-
"Standard Deviation": 0.02125277518,
|
| 1453 |
-
"Rank": 25
|
| 1454 |
-
},
|
| 1455 |
-
"Social": {
|
| 1456 |
-
"Average Score": 0.380021662,
|
| 1457 |
-
"Standard Deviation": 0.04622452748,
|
| 1458 |
-
"Rank": 25
|
| 1459 |
-
},
|
| 1460 |
-
"Chemistry": {
|
| 1461 |
-
"Average Score": 38.27587102395908,
|
| 1462 |
-
"Standard Deviation": null,
|
| 1463 |
-
"Rank": 31
|
| 1464 |
-
},
|
| 1465 |
-
"CPP": {
|
| 1466 |
-
"Average Score": 38.27587102395908,
|
| 1467 |
-
"Standard Deviation": null,
|
| 1468 |
-
"Rank": 32
|
| 1469 |
-
}
|
| 1470 |
-
}
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"config": {
|
| 1474 |
-
"model_name": "gemini-1.0-pro-001",
|
| 1475 |
-
"organization": "Google",
|
| 1476 |
-
"license": "Proprietary",
|
| 1477 |
-
"knowledge_cutoff": "2023/04"
|
| 1478 |
-
},
|
| 1479 |
-
"results": {
|
| 1480 |
-
"OVERALL": {
|
| 1481 |
-
"Average Score": 0.449040654,
|
| 1482 |
-
"Standard Deviation": 0.0450610177,
|
| 1483 |
-
"Rank": 24
|
| 1484 |
-
},
|
| 1485 |
-
"Geometry": {
|
| 1486 |
-
"Average Score": 0.578347959,
|
| 1487 |
-
"Standard Deviation": 0.04242873607,
|
| 1488 |
-
"Rank": 19
|
| 1489 |
-
},
|
| 1490 |
-
"Algebra": {
|
| 1491 |
-
"Average Score": 0.462417786,
|
| 1492 |
-
"Standard Deviation": 0.01668313635,
|
| 1493 |
-
"Rank": 28
|
| 1494 |
-
},
|
| 1495 |
-
"Probability": {
|
| 1496 |
-
"Average Score": 0.289836324,
|
| 1497 |
-
"Standard Deviation": 0.05739831115,
|
| 1498 |
-
"Rank": 37
|
| 1499 |
-
},
|
| 1500 |
-
"Logical": {
|
| 1501 |
-
"Average Score": 0.191140355,
|
| 1502 |
-
"Standard Deviation": 0.03394652499,
|
| 1503 |
-
"Rank": 40
|
| 1504 |
-
},
|
| 1505 |
-
"Social": {
|
| 1506 |
-
"Average Score": 0.130790863,
|
| 1507 |
-
"Standard Deviation": 0.02800188173,
|
| 1508 |
-
"Rank": 45
|
| 1509 |
-
},
|
| 1510 |
-
"Chemistry": {
|
| 1511 |
-
"Average Score": 45.22204471452975,
|
| 1512 |
-
"Standard Deviation": null,
|
| 1513 |
-
"Rank": 22
|
| 1514 |
-
},
|
| 1515 |
-
"CPP": {
|
| 1516 |
-
"Average Score": 45.22204471452975,
|
| 1517 |
-
"Standard Deviation": null,
|
| 1518 |
-
"Rank": 23
|
| 1519 |
-
}
|
| 1520 |
-
}
|
| 1521 |
-
},
|
| 1522 |
-
{
|
| 1523 |
-
"config": {
|
| 1524 |
-
"model_name": "openchat-3.5-0106",
|
| 1525 |
-
"organization": "OpenChat",
|
| 1526 |
-
"license": "Apache-2.0",
|
| 1527 |
-
"knowledge_cutoff": "2024/01"
|
| 1528 |
-
},
|
| 1529 |
-
"results": {
|
| 1530 |
-
"OVERALL": {
|
| 1531 |
-
"Average Score": 0.363929888,
|
| 1532 |
-
"Standard Deviation": 0.08602347145,
|
| 1533 |
-
"Rank": 33
|
| 1534 |
-
},
|
| 1535 |
-
"Geometry": {
|
| 1536 |
-
"Average Score": 0.38715246,
|
| 1537 |
-
"Standard Deviation": 0.03701851946,
|
| 1538 |
-
"Rank": 32
|
| 1539 |
-
},
|
| 1540 |
-
"Algebra": {
|
| 1541 |
-
"Average Score": 0.441233712,
|
| 1542 |
-
"Standard Deviation": 0.01135753754,
|
| 1543 |
-
"Rank": 29
|
| 1544 |
-
},
|
| 1545 |
-
"Probability": {
|
| 1546 |
-
"Average Score": 0.38802618,
|
| 1547 |
-
"Standard Deviation": 0.05663879714,
|
| 1548 |
-
"Rank": 30
|
| 1549 |
-
},
|
| 1550 |
-
"Logical": {
|
| 1551 |
-
"Average Score": 0.336754383,
|
| 1552 |
-
"Standard Deviation": 0.01608478079,
|
| 1553 |
-
"Rank": 28
|
| 1554 |
-
},
|
| 1555 |
-
"Social": {
|
| 1556 |
-
"Average Score": 0.250891608,
|
| 1557 |
-
"Standard Deviation": 0.03253769914,
|
| 1558 |
-
"Rank": 36
|
| 1559 |
-
},
|
| 1560 |
-
"Chemistry": {
|
| 1561 |
-
"Average Score": 33.70639271807677,
|
| 1562 |
-
"Standard Deviation": null,
|
| 1563 |
-
"Rank": 32
|
| 1564 |
-
},
|
| 1565 |
-
"CPP": {
|
| 1566 |
-
"Average Score": 33.70639271807677,
|
| 1567 |
-
"Standard Deviation": null,
|
| 1568 |
-
"Rank": 33
|
| 1569 |
-
}
|
| 1570 |
-
}
|
| 1571 |
-
},
|
| 1572 |
-
{
|
| 1573 |
-
"config": {
|
| 1574 |
-
"model_name": "openchat-3.5",
|
| 1575 |
-
"organization": "OpenChat",
|
| 1576 |
-
"license": "Apache-2.0",
|
| 1577 |
-
"knowledge_cutoff": "2023/11"
|
| 1578 |
-
},
|
| 1579 |
-
"results": {
|
| 1580 |
-
"OVERALL": {
|
| 1581 |
-
"Average Score": 0.361341296,
|
| 1582 |
-
"Standard Deviation": 0.09034869493,
|
| 1583 |
-
"Rank": 34
|
| 1584 |
-
},
|
| 1585 |
-
"Geometry": {
|
| 1586 |
-
"Average Score": 0.401699069,
|
| 1587 |
-
"Standard Deviation": 0.03410726557,
|
| 1588 |
-
"Rank": 30
|
| 1589 |
-
},
|
| 1590 |
-
"Algebra": {
|
| 1591 |
-
"Average Score": 0.414095336,
|
| 1592 |
-
"Standard Deviation": 0.01881964261,
|
| 1593 |
-
"Rank": 31
|
| 1594 |
-
},
|
| 1595 |
-
"Probability": {
|
| 1596 |
-
"Average Score": 0.349601002,
|
| 1597 |
-
"Standard Deviation": 0.05077455539,
|
| 1598 |
-
"Rank": 32
|
| 1599 |
-
},
|
| 1600 |
-
"Logical": {
|
| 1601 |
-
"Average Score": 0.331069242,
|
| 1602 |
-
"Standard Deviation": 0.02180827173,
|
| 1603 |
-
"Rank": 30
|
| 1604 |
-
},
|
| 1605 |
-
"Social": {
|
| 1606 |
-
"Average Score": 0.319991655,
|
| 1607 |
-
"Standard Deviation": 0.04502478724,
|
| 1608 |
-
"Rank": 29
|
| 1609 |
-
},
|
| 1610 |
-
"Chemistry": {
|
| 1611 |
-
"Average Score": 33.020911255646965,
|
| 1612 |
-
"Standard Deviation": null,
|
| 1613 |
-
"Rank": 33
|
| 1614 |
-
},
|
| 1615 |
-
"CPP": {
|
| 1616 |
-
"Average Score": 33.020911255646965,
|
| 1617 |
-
"Standard Deviation": null,
|
| 1618 |
-
"Rank": 34
|
| 1619 |
-
}
|
| 1620 |
-
}
|
| 1621 |
-
},
|
| 1622 |
-
{
|
| 1623 |
-
"config": {
|
| 1624 |
-
"model_name": "command-r-(08-2024)",
|
| 1625 |
-
"organization": "Cohere",
|
| 1626 |
-
"license": "CC-BY-NC-4.0",
|
| 1627 |
-
"knowledge_cutoff": "2024/08"
|
| 1628 |
-
},
|
| 1629 |
-
"results": {
|
| 1630 |
-
"OVERALL": {
|
| 1631 |
-
"Average Score": 0.427605298,
|
| 1632 |
-
"Standard Deviation": 0.01747449163,
|
| 1633 |
-
"Rank": 25
|
| 1634 |
-
},
|
| 1635 |
-
"Geometry": {
|
| 1636 |
-
"Average Score": 0.448300727,
|
| 1637 |
-
"Standard Deviation": 0.04996362328,
|
| 1638 |
-
"Rank": 27
|
| 1639 |
-
},
|
| 1640 |
-
"Algebra": {
|
| 1641 |
-
"Average Score": 0.417519167,
|
| 1642 |
-
"Standard Deviation": 0.01822196902,
|
| 1643 |
-
"Rank": 30
|
| 1644 |
-
},
|
| 1645 |
-
"Probability": {
|
| 1646 |
-
"Average Score": 0.366336281,
|
| 1647 |
-
"Standard Deviation": 0.04716826942,
|
| 1648 |
-
"Rank": 31
|
| 1649 |
-
},
|
| 1650 |
-
"Logical": {
|
| 1651 |
-
"Average Score": 0.214657906,
|
| 1652 |
-
"Standard Deviation": 0.03003579835,
|
| 1653 |
-
"Rank": 37
|
| 1654 |
-
},
|
| 1655 |
-
"Social": {
|
| 1656 |
-
"Average Score": 0.276088379,
|
| 1657 |
-
"Standard Deviation": 0.03295234688,
|
| 1658 |
-
"Rank": 32
|
| 1659 |
-
},
|
| 1660 |
-
"Chemistry": {
|
| 1661 |
-
"Average Score": 39.61492485677676,
|
| 1662 |
-
"Standard Deviation": null,
|
| 1663 |
-
"Rank": 29
|
| 1664 |
-
},
|
| 1665 |
-
"CPP": {
|
| 1666 |
-
"Average Score": 39.61492485677676,
|
| 1667 |
-
"Standard Deviation": null,
|
| 1668 |
-
"Rank": 30
|
| 1669 |
-
}
|
| 1670 |
-
}
|
| 1671 |
-
},
|
| 1672 |
-
{
|
| 1673 |
-
"config": {
|
| 1674 |
-
"model_name": "gemma-1.1-7b-it",
|
| 1675 |
-
"organization": "Google",
|
| 1676 |
-
"license": "Gemma License",
|
| 1677 |
-
"knowledge_cutoff": "2024/02"
|
| 1678 |
-
},
|
| 1679 |
-
"results": {
|
| 1680 |
-
"OVERALL": {
|
| 1681 |
-
"Average Score": 0.339506922,
|
| 1682 |
-
"Standard Deviation": 0.1066279108,
|
| 1683 |
-
"Rank": 36
|
| 1684 |
-
},
|
| 1685 |
-
"Geometry": {
|
| 1686 |
-
"Average Score": 0.324170977,
|
| 1687 |
-
"Standard Deviation": 0.04668553765,
|
| 1688 |
-
"Rank": 35
|
| 1689 |
-
},
|
| 1690 |
-
"Algebra": {
|
| 1691 |
-
"Average Score": 0.398684697,
|
| 1692 |
-
"Standard Deviation": 0.01982398259,
|
| 1693 |
-
"Rank": 32
|
| 1694 |
-
},
|
| 1695 |
-
"Probability": {
|
| 1696 |
-
"Average Score": 0.293253175,
|
| 1697 |
-
"Standard Deviation": 0.05126192191,
|
| 1698 |
-
"Rank": 36
|
| 1699 |
-
},
|
| 1700 |
-
"Logical": {
|
| 1701 |
-
"Average Score": 0.317750796,
|
| 1702 |
-
"Standard Deviation": 0.01101933543,
|
| 1703 |
-
"Rank": 31
|
| 1704 |
-
},
|
| 1705 |
-
"Social": {
|
| 1706 |
-
"Average Score": 0.179073276,
|
| 1707 |
-
"Standard Deviation": 0.02009658805,
|
| 1708 |
-
"Rank": 41
|
| 1709 |
-
},
|
| 1710 |
-
"Chemistry": {
|
| 1711 |
-
"Average Score": 42.666504105798204,
|
| 1712 |
-
"Standard Deviation": null,
|
| 1713 |
-
"Rank": 26
|
| 1714 |
-
},
|
| 1715 |
-
"CPP": {
|
| 1716 |
-
"Average Score": 42.666504105798204,
|
| 1717 |
-
"Standard Deviation": null,
|
| 1718 |
-
"Rank": 27
|
| 1719 |
-
}
|
| 1720 |
-
}
|
| 1721 |
-
},
|
| 1722 |
-
{
|
| 1723 |
-
"config": {
|
| 1724 |
-
"model_name": "llama3-8b-instruct",
|
| 1725 |
-
"organization": "Meta",
|
| 1726 |
-
"license": "Llama 3 Community",
|
| 1727 |
-
"knowledge_cutoff": "2023/03"
|
| 1728 |
-
},
|
| 1729 |
-
"results": {
|
| 1730 |
-
"OVERALL": {
|
| 1731 |
-
"Average Score": 0.367722676,
|
| 1732 |
-
"Standard Deviation": 0.1071368221,
|
| 1733 |
-
"Rank": 31
|
| 1734 |
-
},
|
| 1735 |
-
"Geometry": {
|
| 1736 |
-
"Average Score": 0.367143758,
|
| 1737 |
-
"Standard Deviation": 0.04363680358,
|
| 1738 |
-
"Rank": 33
|
| 1739 |
-
},
|
| 1740 |
-
"Algebra": {
|
| 1741 |
-
"Average Score": 0.391480973,
|
| 1742 |
-
"Standard Deviation": 0.02757445266,
|
| 1743 |
-
"Rank": 33
|
| 1744 |
-
},
|
| 1745 |
-
"Probability": {
|
| 1746 |
-
"Average Score": 0.317616445,
|
| 1747 |
-
"Standard Deviation": 0.04300430361,
|
| 1748 |
-
"Rank": 35
|
| 1749 |
-
},
|
| 1750 |
-
"Logical": {
|
| 1751 |
-
"Average Score": 0.461607495,
|
| 1752 |
-
"Standard Deviation": 0.02185028842,
|
| 1753 |
-
"Rank": 22
|
| 1754 |
-
},
|
| 1755 |
-
"Social": {
|
| 1756 |
-
"Average Score": 0.336373622,
|
| 1757 |
-
"Standard Deviation": 0.05762408512,
|
| 1758 |
-
"Rank": 26
|
| 1759 |
-
},
|
| 1760 |
-
"Chemistry": {
|
| 1761 |
-
"Average Score": 45.35392139264795,
|
| 1762 |
-
"Standard Deviation": null,
|
| 1763 |
-
"Rank": 21
|
| 1764 |
-
},
|
| 1765 |
-
"CPP": {
|
| 1766 |
-
"Average Score": 45.35392139264795,
|
| 1767 |
-
"Standard Deviation": null,
|
| 1768 |
-
"Rank": 22
|
| 1769 |
-
}
|
| 1770 |
-
}
|
| 1771 |
-
},
|
| 1772 |
-
{
|
| 1773 |
-
"config": {
|
| 1774 |
-
"model_name": "gemma-2-2b-it",
|
| 1775 |
-
"organization": "Google",
|
| 1776 |
-
"license": "Gemma License",
|
| 1777 |
-
"knowledge_cutoff": "2024/07"
|
| 1778 |
-
},
|
| 1779 |
-
"results": {
|
| 1780 |
-
"OVERALL": {
|
| 1781 |
-
"Average Score": 0.502167612,
|
| 1782 |
-
"Standard Deviation": 0.04389786763,
|
| 1783 |
-
"Rank": 19
|
| 1784 |
-
},
|
| 1785 |
-
"Geometry": {
|
| 1786 |
-
"Average Score": 0.395006676,
|
| 1787 |
-
"Standard Deviation": 0.05882607713,
|
| 1788 |
-
"Rank": 31
|
| 1789 |
-
},
|
| 1790 |
-
"Algebra": {
|
| 1791 |
-
"Average Score": 0.379391887,
|
| 1792 |
-
"Standard Deviation": 0.01722410785,
|
| 1793 |
-
"Rank": 34
|
| 1794 |
-
},
|
| 1795 |
-
"Probability": {
|
| 1796 |
-
"Average Score": 0.331231097,
|
| 1797 |
-
"Standard Deviation": 0.05392499987,
|
| 1798 |
-
"Rank": 34
|
| 1799 |
-
},
|
| 1800 |
-
"Logical": {
|
| 1801 |
-
"Average Score": 0.367687789,
|
| 1802 |
-
"Standard Deviation": 0.02547968808,
|
| 1803 |
-
"Rank": 26
|
| 1804 |
-
},
|
| 1805 |
-
"Social": {
|
| 1806 |
-
"Average Score": 0.393482094,
|
| 1807 |
-
"Standard Deviation": 0.06450214024,
|
| 1808 |
-
"Rank": 23
|
| 1809 |
-
},
|
| 1810 |
-
"Chemistry": {
|
| 1811 |
-
"Average Score": 30.53406933106768,
|
| 1812 |
-
"Standard Deviation": null,
|
| 1813 |
-
"Rank": 35
|
| 1814 |
-
},
|
| 1815 |
-
"CPP": {
|
| 1816 |
-
"Average Score": 30.53406933106768,
|
| 1817 |
-
"Standard Deviation": null,
|
| 1818 |
-
"Rank": 36
|
| 1819 |
-
}
|
| 1820 |
-
}
|
| 1821 |
-
},
|
| 1822 |
-
{
|
| 1823 |
-
"config": {
|
| 1824 |
-
"model_name": "starling-lm-7b-alpha",
|
| 1825 |
-
"organization": "Nexusflow",
|
| 1826 |
-
"license": "Apache-2.0",
|
| 1827 |
-
"knowledge_cutoff": "2023/11"
|
| 1828 |
-
},
|
| 1829 |
-
"results": {
|
| 1830 |
-
"OVERALL": {
|
| 1831 |
-
"Average Score": 0.366628765,
|
| 1832 |
-
"Standard Deviation": 0.08405492929,
|
| 1833 |
-
"Rank": 32
|
| 1834 |
-
},
|
| 1835 |
-
"Geometry": {
|
| 1836 |
-
"Average Score": 0.336782578,
|
| 1837 |
-
"Standard Deviation": 0.04069449132,
|
| 1838 |
-
"Rank": 34
|
| 1839 |
-
},
|
| 1840 |
-
"Algebra": {
|
| 1841 |
-
"Average Score": 0.371551932,
|
| 1842 |
-
"Standard Deviation": 0.03367241745,
|
| 1843 |
-
"Rank": 35
|
| 1844 |
-
},
|
| 1845 |
-
"Probability": {
|
| 1846 |
-
"Average Score": 0.331472505,
|
| 1847 |
-
"Standard Deviation": 0.04833324282,
|
| 1848 |
-
"Rank": 33
|
| 1849 |
-
},
|
| 1850 |
-
"Logical": {
|
| 1851 |
-
"Average Score": 0.260869624,
|
| 1852 |
-
"Standard Deviation": 0.03562735237,
|
| 1853 |
-
"Rank": 35
|
| 1854 |
-
},
|
| 1855 |
-
"Social": {
|
| 1856 |
-
"Average Score": 0.271975534,
|
| 1857 |
-
"Standard Deviation": 0.04266753408,
|
| 1858 |
-
"Rank": 33
|
| 1859 |
-
},
|
| 1860 |
-
"Chemistry": {
|
| 1861 |
-
"Average Score": 30.07926487356878,
|
| 1862 |
-
"Standard Deviation": null,
|
| 1863 |
-
"Rank": 36
|
| 1864 |
-
},
|
| 1865 |
-
"CPP": {
|
| 1866 |
-
"Average Score": 30.07926487356878,
|
| 1867 |
-
"Standard Deviation": null,
|
| 1868 |
-
"Rank": 37
|
| 1869 |
-
}
|
| 1870 |
-
}
|
| 1871 |
-
},
|
| 1872 |
-
{
|
| 1873 |
-
"config": {
|
| 1874 |
-
"model_name": "qwen1.5-4b-chat",
|
| 1875 |
-
"organization": "Alibaba",
|
| 1876 |
-
"license": "Qianwen LICENSE",
|
| 1877 |
-
"knowledge_cutoff": "2024/02"
|
| 1878 |
-
},
|
| 1879 |
-
"results": {
|
| 1880 |
-
"OVERALL": {
|
| 1881 |
-
"Average Score": 0.111876411,
|
| 1882 |
-
"Standard Deviation": 0.04241022785,
|
| 1883 |
-
"Rank": 48
|
| 1884 |
-
},
|
| 1885 |
-
"Geometry": {
|
| 1886 |
-
"Average Score": 0.215834522,
|
| 1887 |
-
"Standard Deviation": 0.0363766363,
|
| 1888 |
-
"Rank": 39
|
| 1889 |
-
},
|
| 1890 |
-
"Algebra": {
|
| 1891 |
-
"Average Score": 0.305589811,
|
| 1892 |
-
"Standard Deviation": 0.02354198912,
|
| 1893 |
-
"Rank": 36
|
| 1894 |
-
},
|
| 1895 |
-
"Probability": {
|
| 1896 |
-
"Average Score": 0.149365327,
|
| 1897 |
-
"Standard Deviation": 0.03489672675,
|
| 1898 |
-
"Rank": 43
|
| 1899 |
-
},
|
| 1900 |
-
"Logical": {
|
| 1901 |
-
"Average Score": 0.116210168,
|
| 1902 |
-
"Standard Deviation": 0.005927966496,
|
| 1903 |
-
"Rank": 46
|
| 1904 |
-
},
|
| 1905 |
-
"Social": {
|
| 1906 |
-
"Average Score": 0.18195615,
|
| 1907 |
-
"Standard Deviation": 0.02269805277,
|
| 1908 |
-
"Rank": 40
|
| 1909 |
-
},
|
| 1910 |
-
"Chemistry": {
|
| 1911 |
-
"Average Score": 13.21208067122554,
|
| 1912 |
-
"Standard Deviation": null,
|
| 1913 |
-
"Rank": 46
|
| 1914 |
-
},
|
| 1915 |
-
"CPP": {
|
| 1916 |
-
"Average Score": 13.21208067122554,
|
| 1917 |
-
"Standard Deviation": null,
|
| 1918 |
-
"Rank": 47
|
| 1919 |
-
}
|
| 1920 |
-
}
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"config": {
|
| 1924 |
-
"model_name": "command-r-(04-2024)",
|
| 1925 |
-
"organization": "Cohere",
|
| 1926 |
-
"license": "CC-BY-NC-4.0",
|
| 1927 |
-
"knowledge_cutoff": "2024/04"
|
| 1928 |
-
},
|
| 1929 |
-
"results": {
|
| 1930 |
-
"OVERALL": {
|
| 1931 |
-
"Average Score": 0.388783887,
|
| 1932 |
-
"Standard Deviation": 0.07417186783,
|
| 1933 |
-
"Rank": 29
|
| 1934 |
-
},
|
| 1935 |
-
"Geometry": {
|
| 1936 |
-
"Average Score": 0.300416698,
|
| 1937 |
-
"Standard Deviation": 0.03485612736,
|
| 1938 |
-
"Rank": 36
|
| 1939 |
-
},
|
| 1940 |
-
"Algebra": {
|
| 1941 |
-
"Average Score": 0.293120231,
|
| 1942 |
-
"Standard Deviation": 0.032926484,
|
| 1943 |
-
"Rank": 37
|
| 1944 |
-
},
|
| 1945 |
-
"Probability": {
|
| 1946 |
-
"Average Score": 0.281271304,
|
| 1947 |
-
"Standard Deviation": 0.05697149867,
|
| 1948 |
-
"Rank": 38
|
| 1949 |
-
},
|
| 1950 |
-
"Logical": {
|
| 1951 |
-
"Average Score": 0.276189906,
|
| 1952 |
-
"Standard Deviation": 0.03562914754,
|
| 1953 |
-
"Rank": 33
|
| 1954 |
-
},
|
| 1955 |
-
"Social": {
|
| 1956 |
-
"Average Score": 0.283882949,
|
| 1957 |
-
"Standard Deviation": 0.03336901148,
|
| 1958 |
-
"Rank": 31
|
| 1959 |
-
},
|
| 1960 |
-
"Chemistry": {
|
| 1961 |
-
"Average Score": 41.346336503003236,
|
| 1962 |
-
"Standard Deviation": null,
|
| 1963 |
-
"Rank": 27
|
| 1964 |
-
},
|
| 1965 |
-
"CPP": {
|
| 1966 |
-
"Average Score": 41.346336503003236,
|
| 1967 |
-
"Standard Deviation": null,
|
| 1968 |
-
"Rank": 28
|
| 1969 |
-
}
|
| 1970 |
-
}
|
| 1971 |
-
},
|
| 1972 |
-
{
|
| 1973 |
-
"config": {
|
| 1974 |
-
"model_name": "vicuna-33b",
|
| 1975 |
-
"organization": "LMSYS",
|
| 1976 |
-
"license": "Non-commercial",
|
| 1977 |
-
"knowledge_cutoff": "2023/08"
|
| 1978 |
-
},
|
| 1979 |
-
"results": {
|
| 1980 |
-
"OVERALL": {
|
| 1981 |
-
"Average Score": 0.316543555,
|
| 1982 |
-
"Standard Deviation": 0.08922095647,
|
| 1983 |
-
"Rank": 38
|
| 1984 |
-
},
|
| 1985 |
-
"Geometry": {
|
| 1986 |
-
"Average Score": 0.208284679,
|
| 1987 |
-
"Standard Deviation": 0.03937771461,
|
| 1988 |
-
"Rank": 40
|
| 1989 |
-
},
|
| 1990 |
-
"Algebra": {
|
| 1991 |
-
"Average Score": 0.248994048,
|
| 1992 |
-
"Standard Deviation": 0.02668175054,
|
| 1993 |
-
"Rank": 39
|
| 1994 |
-
},
|
| 1995 |
-
"Probability": {
|
| 1996 |
-
"Average Score": 0.222313995,
|
| 1997 |
-
"Standard Deviation": 0.03978859759,
|
| 1998 |
-
"Rank": 41
|
| 1999 |
-
},
|
| 2000 |
-
"Logical": {
|
| 2001 |
-
"Average Score": 0.180291222,
|
| 2002 |
-
"Standard Deviation": 0.021886267,
|
| 2003 |
-
"Rank": 41
|
| 2004 |
-
},
|
| 2005 |
-
"Social": {
|
| 2006 |
-
"Average Score": 0.257623798,
|
| 2007 |
-
"Standard Deviation": 0.02653724437,
|
| 2008 |
-
"Rank": 34
|
| 2009 |
-
},
|
| 2010 |
-
"Chemistry": {
|
| 2011 |
-
"Average Score": 28.01838653090379,
|
| 2012 |
-
"Standard Deviation": null,
|
| 2013 |
-
"Rank": 37
|
| 2014 |
-
},
|
| 2015 |
-
"CPP": {
|
| 2016 |
-
"Average Score": 28.01838653090379,
|
| 2017 |
-
"Standard Deviation": null,
|
| 2018 |
-
"Rank": 38
|
| 2019 |
-
}
|
| 2020 |
-
}
|
| 2021 |
-
},
|
| 2022 |
-
{
|
| 2023 |
-
"config": {
|
| 2024 |
-
"model_name": "gemma-7b-it",
|
| 2025 |
-
"organization": "Google",
|
| 2026 |
-
"license": "Gemma License",
|
| 2027 |
-
"knowledge_cutoff": "2024/02"
|
| 2028 |
-
},
|
| 2029 |
-
"results": {
|
| 2030 |
-
"OVERALL": {
|
| 2031 |
-
"Average Score": 0.285077558,
|
| 2032 |
-
"Standard Deviation": 0.08871758453,
|
| 2033 |
-
"Rank": 40
|
| 2034 |
-
},
|
| 2035 |
-
"Geometry": {
|
| 2036 |
-
"Average Score": 0.244791417,
|
| 2037 |
-
"Standard Deviation": 0.0289612078,
|
| 2038 |
-
"Rank": 37
|
| 2039 |
-
},
|
| 2040 |
-
"Algebra": {
|
| 2041 |
-
"Average Score": 0.250614794,
|
| 2042 |
-
"Standard Deviation": 0.01991678295,
|
| 2043 |
-
"Rank": 38
|
| 2044 |
-
},
|
| 2045 |
-
"Probability": {
|
| 2046 |
-
"Average Score": 0.174313053,
|
| 2047 |
-
"Standard Deviation": 0.03765424728,
|
| 2048 |
-
"Rank": 42
|
| 2049 |
-
},
|
| 2050 |
-
"Logical": {
|
| 2051 |
-
"Average Score": 0.197505536,
|
| 2052 |
-
"Standard Deviation": 0.02050298885,
|
| 2053 |
-
"Rank": 38
|
| 2054 |
-
},
|
| 2055 |
-
"Social": {
|
| 2056 |
-
"Average Score": 0.202138025,
|
| 2057 |
-
"Standard Deviation": 0.02098346639,
|
| 2058 |
-
"Rank": 39
|
| 2059 |
-
},
|
| 2060 |
-
"Chemistry": {
|
| 2061 |
-
"Average Score": 28.014658234926813,
|
| 2062 |
-
"Standard Deviation": null,
|
| 2063 |
-
"Rank": 38
|
| 2064 |
-
},
|
| 2065 |
-
"CPP": {
|
| 2066 |
-
"Average Score": 28.014658234926813,
|
| 2067 |
-
"Standard Deviation": null,
|
| 2068 |
-
"Rank": 39
|
| 2069 |
-
}
|
| 2070 |
-
}
|
| 2071 |
-
},
|
| 2072 |
-
{
|
| 2073 |
-
"config": {
|
| 2074 |
-
"model_name": "mistral-7b-instruct-2",
|
| 2075 |
-
"organization": "Mistral",
|
| 2076 |
-
"license": "Apache 2.0",
|
| 2077 |
-
"knowledge_cutoff": "2023/12"
|
| 2078 |
-
},
|
| 2079 |
-
"results": {
|
| 2080 |
-
"OVERALL": {
|
| 2081 |
-
"Average Score": 0.427513868,
|
| 2082 |
-
"Standard Deviation": 0.05553921135,
|
| 2083 |
-
"Rank": 26
|
| 2084 |
-
},
|
| 2085 |
-
"Geometry": {
|
| 2086 |
-
"Average Score": 0.216402626,
|
| 2087 |
-
"Standard Deviation": 0.03338414918,
|
| 2088 |
-
"Rank": 38
|
| 2089 |
-
},
|
| 2090 |
-
"Algebra": {
|
| 2091 |
-
"Average Score": 0.233777838,
|
| 2092 |
-
"Standard Deviation": 0.0155226054,
|
| 2093 |
-
"Rank": 40
|
| 2094 |
-
},
|
| 2095 |
-
"Probability": {
|
| 2096 |
-
"Average Score": 0.25118175,
|
| 2097 |
-
"Standard Deviation": 0.04065514593,
|
| 2098 |
-
"Rank": 39
|
| 2099 |
-
},
|
| 2100 |
-
"Logical": {
|
| 2101 |
-
"Average Score": 0.224469136,
|
| 2102 |
-
"Standard Deviation": 0.03404706752,
|
| 2103 |
-
"Rank": 36
|
| 2104 |
-
},
|
| 2105 |
-
"Social": {
|
| 2106 |
-
"Average Score": 0.209386782,
|
| 2107 |
-
"Standard Deviation": 0.02738569921,
|
| 2108 |
-
"Rank": 38
|
| 2109 |
-
},
|
| 2110 |
-
"Chemistry": {
|
| 2111 |
-
"Average Score": 31.382959631870822,
|
| 2112 |
-
"Standard Deviation": null,
|
| 2113 |
-
"Rank": 34
|
| 2114 |
-
},
|
| 2115 |
-
"CPP": {
|
| 2116 |
-
"Average Score": 31.382959631870822,
|
| 2117 |
-
"Standard Deviation": null,
|
| 2118 |
-
"Rank": 35
|
| 2119 |
-
}
|
| 2120 |
-
}
|
| 2121 |
-
},
|
| 2122 |
-
{
|
| 2123 |
-
"config": {
|
| 2124 |
-
"model_name": "mistral-7b-instruct-1",
|
| 2125 |
-
"organization": "Mistral",
|
| 2126 |
-
"license": "Apache 2.0",
|
| 2127 |
-
"knowledge_cutoff": "2023/12"
|
| 2128 |
-
},
|
| 2129 |
-
"results": {
|
| 2130 |
-
"OVERALL": {
|
| 2131 |
-
"Average Score": 0.23016314,
|
| 2132 |
-
"Standard Deviation": 0.07137625271,
|
| 2133 |
-
"Rank": 45
|
| 2134 |
-
},
|
| 2135 |
-
"Geometry": {
|
| 2136 |
-
"Average Score": 0.161799938,
|
| 2137 |
-
"Standard Deviation": 0.03595278559,
|
| 2138 |
-
"Rank": 44
|
| 2139 |
-
},
|
| 2140 |
-
"Algebra": {
|
| 2141 |
-
"Average Score": 0.210341624,
|
| 2142 |
-
"Standard Deviation": 0.01736539119,
|
| 2143 |
-
"Rank": 41
|
| 2144 |
-
},
|
| 2145 |
-
"Probability": {
|
| 2146 |
-
"Average Score": 0.238417922,
|
| 2147 |
-
"Standard Deviation": 0.03744211933,
|
| 2148 |
-
"Rank": 40
|
| 2149 |
-
},
|
| 2150 |
-
"Logical": {
|
| 2151 |
-
"Average Score": 0.142636601,
|
| 2152 |
-
"Standard Deviation": 0.02080406365,
|
| 2153 |
-
"Rank": 45
|
| 2154 |
-
},
|
| 2155 |
-
"Social": {
|
| 2156 |
-
"Average Score": 0.117646827,
|
| 2157 |
-
"Standard Deviation": 0.009321202779,
|
| 2158 |
-
"Rank": 47
|
| 2159 |
-
},
|
| 2160 |
-
"Chemistry": {
|
| 2161 |
-
"Average Score": 18.929093202755805,
|
| 2162 |
-
"Standard Deviation": null,
|
| 2163 |
-
"Rank": 41
|
| 2164 |
-
},
|
| 2165 |
-
"CPP": {
|
| 2166 |
-
"Average Score": 18.929093202755805,
|
| 2167 |
-
"Standard Deviation": null,
|
| 2168 |
-
"Rank": 42
|
| 2169 |
-
}
|
| 2170 |
-
}
|
| 2171 |
-
},
|
| 2172 |
-
{
|
| 2173 |
-
"config": {
|
| 2174 |
-
"model_name": "vicuna-13b",
|
| 2175 |
-
"organization": "LMSYS",
|
| 2176 |
-
"license": "Non-commercial",
|
| 2177 |
-
"knowledge_cutoff": "2023/07"
|
| 2178 |
-
},
|
| 2179 |
-
"results": {
|
| 2180 |
-
"OVERALL": {
|
| 2181 |
-
"Average Score": 0.201892849,
|
| 2182 |
-
"Standard Deviation": 0.06021749802,
|
| 2183 |
-
"Rank": 46
|
| 2184 |
-
},
|
| 2185 |
-
"Geometry": {
|
| 2186 |
-
"Average Score": 0.200941928,
|
| 2187 |
-
"Standard Deviation": 0.03366817781,
|
| 2188 |
-
"Rank": 41
|
| 2189 |
-
},
|
| 2190 |
-
"Algebra": {
|
| 2191 |
-
"Average Score": 0.196123323,
|
| 2192 |
-
"Standard Deviation": 0.0135715643,
|
| 2193 |
-
"Rank": 42
|
| 2194 |
-
},
|
| 2195 |
-
"Probability": {
|
| 2196 |
-
"Average Score": 0.141214079,
|
| 2197 |
-
"Standard Deviation": 0.02721328211,
|
| 2198 |
-
"Rank": 44
|
| 2199 |
-
},
|
| 2200 |
-
"Logical": {
|
| 2201 |
-
"Average Score": 0.148598631,
|
| 2202 |
-
"Standard Deviation": 0.02241523892,
|
| 2203 |
-
"Rank": 43
|
| 2204 |
-
},
|
| 2205 |
-
"Social": {
|
| 2206 |
-
"Average Score": 0.124655135,
|
| 2207 |
-
"Standard Deviation": 0.01122382671,
|
| 2208 |
-
"Rank": 46
|
| 2209 |
-
},
|
| 2210 |
-
"Chemistry": {
|
| 2211 |
-
"Average Score": 21.840013221590294,
|
| 2212 |
-
"Standard Deviation": null,
|
| 2213 |
-
"Rank": 39
|
| 2214 |
-
},
|
| 2215 |
-
"CPP": {
|
| 2216 |
-
"Average Score": 21.840013221590294,
|
| 2217 |
-
"Standard Deviation": null,
|
| 2218 |
-
"Rank": 40
|
| 2219 |
-
}
|
| 2220 |
-
}
|
| 2221 |
-
},
|
| 2222 |
-
{
|
| 2223 |
-
"config": {
|
| 2224 |
-
"model_name": "zephyr-7b-beta",
|
| 2225 |
-
"organization": "HuggingFace",
|
| 2226 |
-
"license": "MIT",
|
| 2227 |
-
"knowledge_cutoff": "2023/10"
|
| 2228 |
-
},
|
| 2229 |
-
"results": {
|
| 2230 |
-
"OVERALL": {
|
| 2231 |
-
"Average Score": 0.102705119,
|
| 2232 |
-
"Standard Deviation": 0.03683757312,
|
| 2233 |
-
"Rank": 49
|
| 2234 |
-
},
|
| 2235 |
-
"Geometry": {
|
| 2236 |
-
"Average Score": 0.114005544,
|
| 2237 |
-
"Standard Deviation": 0.03144354365,
|
| 2238 |
-
"Rank": 45
|
| 2239 |
-
},
|
| 2240 |
-
"Algebra": {
|
| 2241 |
-
"Average Score": 0.141766633,
|
| 2242 |
-
"Standard Deviation": 0.03179520129,
|
| 2243 |
-
"Rank": 43
|
| 2244 |
-
},
|
| 2245 |
-
"Probability": {
|
| 2246 |
-
"Average Score": 0.089050714,
|
| 2247 |
-
"Standard Deviation": 0.002136754266,
|
| 2248 |
-
"Rank": 47
|
| 2249 |
-
},
|
| 2250 |
-
"Logical": {
|
| 2251 |
-
"Average Score": 0.069520789,
|
| 2252 |
-
"Standard Deviation": 0.004477840857,
|
| 2253 |
-
"Rank": 50
|
| 2254 |
-
},
|
| 2255 |
-
"Social": {
|
| 2256 |
-
"Average Score": 0.0,
|
| 2257 |
-
"Standard Deviation": 0.0,
|
| 2258 |
-
"Rank": 52
|
| 2259 |
-
},
|
| 2260 |
-
"Chemistry": {
|
| 2261 |
-
"Average Score": 18.92902220864132,
|
| 2262 |
-
"Standard Deviation": null,
|
| 2263 |
-
"Rank": 42
|
| 2264 |
-
},
|
| 2265 |
-
"CPP": {
|
| 2266 |
-
"Average Score": 18.92902220864132,
|
| 2267 |
-
"Standard Deviation": null,
|
| 2268 |
-
"Rank": 43
|
| 2269 |
-
}
|
| 2270 |
-
}
|
| 2271 |
-
},
|
| 2272 |
-
{
|
| 2273 |
-
"config": {
|
| 2274 |
-
"model_name": "gemma-1.1-2b-it",
|
| 2275 |
-
"organization": "Google",
|
| 2276 |
-
"license": "Gemma License",
|
| 2277 |
-
"knowledge_cutoff": "2024/02"
|
| 2278 |
-
},
|
| 2279 |
-
"results": {
|
| 2280 |
-
"OVERALL": {
|
| 2281 |
-
"Average Score": 0.257700845,
|
| 2282 |
-
"Standard Deviation": 0.07369021445,
|
| 2283 |
-
"Rank": 43
|
| 2284 |
-
},
|
| 2285 |
-
"Geometry": {
|
| 2286 |
-
"Average Score": 0.183974034,
|
| 2287 |
-
"Standard Deviation": 0.0215548886,
|
| 2288 |
-
"Rank": 43
|
| 2289 |
-
},
|
| 2290 |
-
"Algebra": {
|
| 2291 |
-
"Average Score": 0.13422252,
|
| 2292 |
-
"Standard Deviation": 0.01922819511,
|
| 2293 |
-
"Rank": 44
|
| 2294 |
-
},
|
| 2295 |
-
"Probability": {
|
| 2296 |
-
"Average Score": 0.095628657,
|
| 2297 |
-
"Standard Deviation": 0.007536076456,
|
| 2298 |
-
"Rank": 46
|
| 2299 |
-
},
|
| 2300 |
-
"Logical": {
|
| 2301 |
-
"Average Score": 0.094965074,
|
| 2302 |
-
"Standard Deviation": 0.005019175487,
|
| 2303 |
-
"Rank": 48
|
| 2304 |
-
},
|
| 2305 |
-
"Social": {
|
| 2306 |
-
"Average Score": 0.167796727,
|
| 2307 |
-
"Standard Deviation": 0.01666541942,
|
| 2308 |
-
"Rank": 42
|
| 2309 |
-
},
|
| 2310 |
-
"Chemistry": {
|
| 2311 |
-
"Average Score": 20.724691953843916,
|
| 2312 |
-
"Standard Deviation": null,
|
| 2313 |
-
"Rank": 40
|
| 2314 |
-
},
|
| 2315 |
-
"CPP": {
|
| 2316 |
-
"Average Score": 20.724691953843916,
|
| 2317 |
-
"Standard Deviation": null,
|
| 2318 |
-
"Rank": 41
|
| 2319 |
-
}
|
| 2320 |
-
}
|
| 2321 |
-
},
|
| 2322 |
-
{
|
| 2323 |
-
"config": {
|
| 2324 |
-
"model_name": "llama2-7b-chat",
|
| 2325 |
-
"organization": "Meta",
|
| 2326 |
-
"license": "Llama 2 Community",
|
| 2327 |
-
"knowledge_cutoff": "2023/07"
|
| 2328 |
-
},
|
| 2329 |
-
"results": {
|
| 2330 |
-
"OVERALL": {
|
| 2331 |
-
"Average Score": 0.260189428,
|
| 2332 |
-
"Standard Deviation": 0.08019299364,
|
| 2333 |
-
"Rank": 42
|
| 2334 |
-
},
|
| 2335 |
-
"Geometry": {
|
| 2336 |
-
"Average Score": 0.087067276,
|
| 2337 |
-
"Standard Deviation": 0.04274343402,
|
| 2338 |
-
"Rank": 46
|
| 2339 |
-
},
|
| 2340 |
-
"Algebra": {
|
| 2341 |
-
"Average Score": 0.12308805,
|
| 2342 |
-
"Standard Deviation": 0.01856053622,
|
| 2343 |
-
"Rank": 45
|
| 2344 |
-
},
|
| 2345 |
-
"Probability": {
|
| 2346 |
-
"Average Score": 0.087515438,
|
| 2347 |
-
"Standard Deviation": 0.006315053573,
|
| 2348 |
-
"Rank": 48
|
| 2349 |
-
},
|
| 2350 |
-
"Logical": {
|
| 2351 |
-
"Average Score": 0.17312827,
|
| 2352 |
-
"Standard Deviation": 0.01867044092,
|
| 2353 |
-
"Rank": 42
|
| 2354 |
-
},
|
| 2355 |
-
"Social": {
|
| 2356 |
-
"Average Score": 0.152905272,
|
| 2357 |
-
"Standard Deviation": 0.007166957097,
|
| 2358 |
-
"Rank": 43
|
| 2359 |
-
},
|
| 2360 |
-
"Chemistry": {
|
| 2361 |
-
"Average Score": 15.730513733660898,
|
| 2362 |
-
"Standard Deviation": null,
|
| 2363 |
-
"Rank": 44
|
| 2364 |
-
},
|
| 2365 |
-
"CPP": {
|
| 2366 |
-
"Average Score": 15.730513733660898,
|
| 2367 |
-
"Standard Deviation": null,
|
| 2368 |
-
"Rank": 45
|
| 2369 |
-
}
|
| 2370 |
-
}
|
| 2371 |
-
},
|
| 2372 |
-
{
|
| 2373 |
-
"config": {
|
| 2374 |
-
"model_name": "gemma-2b-it",
|
| 2375 |
-
"organization": "Google",
|
| 2376 |
-
"license": "Gemma License",
|
| 2377 |
-
"knowledge_cutoff": "2024/02"
|
| 2378 |
-
},
|
| 2379 |
-
"results": {
|
| 2380 |
-
"OVERALL": {
|
| 2381 |
-
"Average Score": 0.234172069,
|
| 2382 |
-
"Standard Deviation": 0.06522685718,
|
| 2383 |
-
"Rank": 44
|
| 2384 |
-
},
|
| 2385 |
-
"Geometry": {
|
| 2386 |
-
"Average Score": 0.198571153,
|
| 2387 |
-
"Standard Deviation": 0.01699161031,
|
| 2388 |
-
"Rank": 42
|
| 2389 |
-
},
|
| 2390 |
-
"Algebra": {
|
| 2391 |
-
"Average Score": 0.109883009,
|
| 2392 |
-
"Standard Deviation": 0.01520005833,
|
| 2393 |
-
"Rank": 46
|
| 2394 |
-
},
|
| 2395 |
-
"Probability": {
|
| 2396 |
-
"Average Score": 0.06467432,
|
| 2397 |
-
"Standard Deviation": 0.002117497231,
|
| 2398 |
-
"Rank": 50
|
| 2399 |
-
},
|
| 2400 |
-
"Logical": {
|
| 2401 |
-
"Average Score": 0.039624492,
|
| 2402 |
-
"Standard Deviation": 0.007606972686,
|
| 2403 |
-
"Rank": 51
|
| 2404 |
-
},
|
| 2405 |
-
"Social": {
|
| 2406 |
-
"Average Score": 0.087452913,
|
| 2407 |
-
"Standard Deviation": 0.008170146562,
|
| 2408 |
-
"Rank": 50
|
| 2409 |
-
},
|
| 2410 |
-
"Chemistry": {
|
| 2411 |
-
"Average Score": 17.2715657115764,
|
| 2412 |
-
"Standard Deviation": null,
|
| 2413 |
-
"Rank": 43
|
| 2414 |
-
},
|
| 2415 |
-
"CPP": {
|
| 2416 |
-
"Average Score": 17.2715657115764,
|
| 2417 |
-
"Standard Deviation": null,
|
| 2418 |
-
"Rank": 44
|
| 2419 |
-
}
|
| 2420 |
-
}
|
| 2421 |
-
},
|
| 2422 |
-
{
|
| 2423 |
-
"config": {
|
| 2424 |
-
"model_name": "llama2-13b-chat",
|
| 2425 |
-
"organization": "Meta",
|
| 2426 |
-
"license": "Llama 2 Community",
|
| 2427 |
-
"knowledge_cutoff": "2023/07"
|
| 2428 |
-
},
|
| 2429 |
-
"results": {
|
| 2430 |
-
"OVERALL": {
|
| 2431 |
-
"Average Score": 0.263305684,
|
| 2432 |
-
"Standard Deviation": 0.07283640689,
|
| 2433 |
-
"Rank": 41
|
| 2434 |
-
},
|
| 2435 |
-
"Geometry": {
|
| 2436 |
-
"Average Score": 0.072729954,
|
| 2437 |
-
"Standard Deviation": 0.02315988261,
|
| 2438 |
-
"Rank": 48
|
| 2439 |
-
},
|
| 2440 |
-
"Algebra": {
|
| 2441 |
-
"Average Score": 0.080371692,
|
| 2442 |
-
"Standard Deviation": 0.01277569453,
|
| 2443 |
-
"Rank": 47
|
| 2444 |
-
},
|
| 2445 |
-
"Probability": {
|
| 2446 |
-
"Average Score": 0.117757344,
|
| 2447 |
-
"Standard Deviation": 0.02418619619,
|
| 2448 |
-
"Rank": 45
|
| 2449 |
-
},
|
| 2450 |
-
"Logical": {
|
| 2451 |
-
"Average Score": 0.193149889,
|
| 2452 |
-
"Standard Deviation": 0.01776690764,
|
| 2453 |
-
"Rank": 39
|
| 2454 |
-
},
|
| 2455 |
-
"Social": {
|
| 2456 |
-
"Average Score": 0.149125922,
|
| 2457 |
-
"Standard Deviation": 0.01157416827,
|
| 2458 |
-
"Rank": 44
|
| 2459 |
-
},
|
| 2460 |
-
"Chemistry": {
|
| 2461 |
-
"Average Score": 13.17258252933903,
|
| 2462 |
-
"Standard Deviation": null,
|
| 2463 |
-
"Rank": 47
|
| 2464 |
-
},
|
| 2465 |
-
"CPP": {
|
| 2466 |
-
"Average Score": 13.17258252933903,
|
| 2467 |
-
"Standard Deviation": null,
|
| 2468 |
-
"Rank": 48
|
| 2469 |
-
}
|
| 2470 |
-
}
|
| 2471 |
-
},
|
| 2472 |
-
{
|
| 2473 |
-
"config": {
|
| 2474 |
-
"model_name": "vicuna-7b",
|
| 2475 |
-
"organization": "LMSYS",
|
| 2476 |
-
"license": "Non-commercial",
|
| 2477 |
-
"knowledge_cutoff": "2023/07"
|
| 2478 |
-
},
|
| 2479 |
-
"results": {
|
| 2480 |
-
"OVERALL": {
|
| 2481 |
-
"Average Score": 0.198839786,
|
| 2482 |
-
"Standard Deviation": 0.05725381576,
|
| 2483 |
-
"Rank": 47
|
| 2484 |
-
},
|
| 2485 |
-
"Geometry": {
|
| 2486 |
-
"Average Score": 0.083457058,
|
| 2487 |
-
"Standard Deviation": 0.02520989111,
|
| 2488 |
-
"Rank": 47
|
| 2489 |
-
},
|
| 2490 |
-
"Algebra": {
|
| 2491 |
-
"Average Score": 0.070883882,
|
| 2492 |
-
"Standard Deviation": 0.007315853253,
|
| 2493 |
-
"Rank": 48
|
| 2494 |
-
},
|
| 2495 |
-
"Probability": {
|
| 2496 |
-
"Average Score": 0.080987673,
|
| 2497 |
-
"Standard Deviation": 0.005474288861,
|
| 2498 |
-
"Rank": 49
|
| 2499 |
-
},
|
| 2500 |
-
"Logical": {
|
| 2501 |
-
"Average Score": 0.100065588,
|
| 2502 |
-
"Standard Deviation": 0.003561886452,
|
| 2503 |
-
"Rank": 47
|
| 2504 |
-
},
|
| 2505 |
-
"Social": {
|
| 2506 |
-
"Average Score": 0.111076414,
|
| 2507 |
-
"Standard Deviation": 0.004805626512,
|
| 2508 |
-
"Rank": 48
|
| 2509 |
-
},
|
| 2510 |
-
"Chemistry": {
|
| 2511 |
-
"Average Score": 14.255194156624162,
|
| 2512 |
-
"Standard Deviation": null,
|
| 2513 |
-
"Rank": 45
|
| 2514 |
-
},
|
| 2515 |
-
"CPP": {
|
| 2516 |
-
"Average Score": 14.255194156624162,
|
| 2517 |
-
"Standard Deviation": null,
|
| 2518 |
-
"Rank": 46
|
| 2519 |
-
}
|
| 2520 |
-
}
|
| 2521 |
-
},
|
| 2522 |
-
{
|
| 2523 |
-
"config": {
|
| 2524 |
-
"model_name": "koala-13b",
|
| 2525 |
-
"organization": "UC Berkeley",
|
| 2526 |
-
"license": "Non-commercial",
|
| 2527 |
-
"knowledge_cutoff": "2023/04"
|
| 2528 |
-
},
|
| 2529 |
-
"results": {
|
| 2530 |
-
"OVERALL": {
|
| 2531 |
-
"Average Score": 0.09387188,
|
| 2532 |
-
"Standard Deviation": 0.02642167489,
|
| 2533 |
-
"Rank": 50
|
| 2534 |
-
},
|
| 2535 |
-
"Geometry": {
|
| 2536 |
-
"Average Score": 0.017374001,
|
| 2537 |
-
"Standard Deviation": 0.01747053557,
|
| 2538 |
-
"Rank": 49
|
| 2539 |
-
},
|
| 2540 |
-
"Algebra": {
|
| 2541 |
-
"Average Score": 0.018129197,
|
| 2542 |
-
"Standard Deviation": 0.01054371383,
|
| 2543 |
-
"Rank": 49
|
| 2544 |
-
},
|
| 2545 |
-
"Probability": {
|
| 2546 |
-
"Average Score": 0.043654362,
|
| 2547 |
-
"Standard Deviation": 0.004288231886,
|
| 2548 |
-
"Rank": 51
|
| 2549 |
-
},
|
| 2550 |
-
"Logical": {
|
| 2551 |
-
"Average Score": 0.074694053,
|
| 2552 |
-
"Standard Deviation": 0.002674646998,
|
| 2553 |
-
"Rank": 49
|
| 2554 |
-
},
|
| 2555 |
-
"Social": {
|
| 2556 |
-
"Average Score": 0.096983835,
|
| 2557 |
-
"Standard Deviation": 0.007847059783,
|
| 2558 |
-
"Rank": 49
|
| 2559 |
-
},
|
| 2560 |
-
"Chemistry": {
|
| 2561 |
-
"Average Score": 6.36433272373514,
|
| 2562 |
-
"Standard Deviation": null,
|
| 2563 |
-
"Rank": 48
|
| 2564 |
-
},
|
| 2565 |
-
"CPP": {
|
| 2566 |
-
"Average Score": 6.36433272373514,
|
| 2567 |
-
"Standard Deviation": null,
|
| 2568 |
-
"Rank": 49
|
| 2569 |
-
}
|
| 2570 |
-
}
|
| 2571 |
-
},
|
| 2572 |
-
{
|
| 2573 |
-
"config": {
|
| 2574 |
-
"model_name": "openassistant-pythia-12b",
|
| 2575 |
-
"organization": "OpenAssistant",
|
| 2576 |
-
"license": "Non-commercial",
|
| 2577 |
-
"knowledge_cutoff": "2023/04"
|
| 2578 |
-
},
|
| 2579 |
-
"results": {
|
| 2580 |
-
"OVERALL": {
|
| 2581 |
-
"Average Score": 0.0,
|
| 2582 |
-
"Standard Deviation": 0.0,
|
| 2583 |
-
"Rank": 51
|
| 2584 |
-
},
|
| 2585 |
-
"Geometry": {
|
| 2586 |
-
"Average Score": 0.0,
|
| 2587 |
-
"Standard Deviation": 0.0,
|
| 2588 |
-
"Rank": 50
|
| 2589 |
-
},
|
| 2590 |
-
"Algebra": {
|
| 2591 |
-
"Average Score": 0.0,
|
| 2592 |
-
"Standard Deviation": 0.0,
|
| 2593 |
-
"Rank": 50
|
| 2594 |
-
},
|
| 2595 |
-
"Probability": {
|
| 2596 |
-
"Average Score": 0.0,
|
| 2597 |
-
"Standard Deviation": 0.0,
|
| 2598 |
-
"Rank": 52
|
| 2599 |
-
},
|
| 2600 |
-
"Logical": {
|
| 2601 |
-
"Average Score": 0.0,
|
| 2602 |
-
"Standard Deviation": 0.0,
|
| 2603 |
-
"Rank": 52
|
| 2604 |
-
},
|
| 2605 |
-
"Social": {
|
| 2606 |
-
"Average Score": 0.030792528,
|
| 2607 |
-
"Standard Deviation": 0.007518796391,
|
| 2608 |
-
"Rank": 51
|
| 2609 |
-
},
|
| 2610 |
-
"Chemistry": {
|
| 2611 |
-
"Average Score": 0.0,
|
| 2612 |
-
"Standard Deviation": null,
|
| 2613 |
-
"Rank": 49
|
| 2614 |
-
},
|
| 2615 |
-
"CPP": {
|
| 2616 |
-
"Average Score": 0.0,
|
| 2617 |
-
"Standard Deviation": null,
|
| 2618 |
-
"Rank": 50
|
| 2619 |
-
}
|
| 2620 |
-
}
|
| 2621 |
-
}
|
| 2622 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/models_2024-10-18-14:06:13.588399.json
DELETED
|
@@ -1,2732 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"config": {
|
| 4 |
-
"model_name": "ChatGPT-4o-latest (2024-09-03)",
|
| 5 |
-
"organization": "OpenAI",
|
| 6 |
-
"license": "Proprietary",
|
| 7 |
-
"knowledge_cutoff": "2023/10"
|
| 8 |
-
},
|
| 9 |
-
"results": {
|
| 10 |
-
"OVERALL": {
|
| 11 |
-
"Average Score": 87.33082346779815,
|
| 12 |
-
"Standard Deviation": 1.4853337406399776,
|
| 13 |
-
"Rank": 3
|
| 14 |
-
},
|
| 15 |
-
"Geometry": {
|
| 16 |
-
"Average Score": 0.976028578,
|
| 17 |
-
"Standard Deviation": 0.01507912373,
|
| 18 |
-
"Rank": 3
|
| 19 |
-
},
|
| 20 |
-
"Algebra": {
|
| 21 |
-
"Average Score": 0.951199453,
|
| 22 |
-
"Standard Deviation": 0.08452452108,
|
| 23 |
-
"Rank": 3
|
| 24 |
-
},
|
| 25 |
-
"Probability": {
|
| 26 |
-
"Average Score": 80.1332207690739,
|
| 27 |
-
"Standard Deviation": null,
|
| 28 |
-
"Rank": 7
|
| 29 |
-
},
|
| 30 |
-
"Logical": {
|
| 31 |
-
"Average Score": 84.12975867250425,
|
| 32 |
-
"Standard Deviation": 0.21211547702245045,
|
| 33 |
-
"Rank": 6
|
| 34 |
-
},
|
| 35 |
-
"Social": {
|
| 36 |
-
"Average Score": 0.815902987,
|
| 37 |
-
"Standard Deviation": 0.0196254222,
|
| 38 |
-
"Rank": 3
|
| 39 |
-
},
|
| 40 |
-
"Chemistry": {
|
| 41 |
-
"Average Score": 89.92480228064885,
|
| 42 |
-
"Standard Deviation": null,
|
| 43 |
-
"Rank": 4
|
| 44 |
-
},
|
| 45 |
-
"CPP": {
|
| 46 |
-
"Average Score": 100.0,
|
| 47 |
-
"Standard Deviation": null,
|
| 48 |
-
"Rank": 1
|
| 49 |
-
}
|
| 50 |
-
}
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"config": {
|
| 54 |
-
"model_name": "gpt-4o-2024-08-06",
|
| 55 |
-
"organization": "OpenAI",
|
| 56 |
-
"license": "Proprietary",
|
| 57 |
-
"knowledge_cutoff": "2023/10"
|
| 58 |
-
},
|
| 59 |
-
"results": {
|
| 60 |
-
"OVERALL": {
|
| 61 |
-
"Average Score": 77.7818546246671,
|
| 62 |
-
"Standard Deviation": 2.7097581088879505,
|
| 63 |
-
"Rank": 5
|
| 64 |
-
},
|
| 65 |
-
"Geometry": {
|
| 66 |
-
"Average Score": 0.99773096,
|
| 67 |
-
"Standard Deviation": 0.002835555172,
|
| 68 |
-
"Rank": 1
|
| 69 |
-
},
|
| 70 |
-
"Algebra": {
|
| 71 |
-
"Average Score": 1.0,
|
| 72 |
-
"Standard Deviation": 0.0,
|
| 73 |
-
"Rank": 1
|
| 74 |
-
},
|
| 75 |
-
"Probability": {
|
| 76 |
-
"Average Score": 74.97136205481755,
|
| 77 |
-
"Standard Deviation": null,
|
| 78 |
-
"Rank": 11
|
| 79 |
-
},
|
| 80 |
-
"Logical": {
|
| 81 |
-
"Average Score": 66.0597109743056,
|
| 82 |
-
"Standard Deviation": 1.5021351704575163,
|
| 83 |
-
"Rank": 14
|
| 84 |
-
},
|
| 85 |
-
"Social": {
|
| 86 |
-
"Average Score": 0.680417314,
|
| 87 |
-
"Standard Deviation": 0.00656867063,
|
| 88 |
-
"Rank": 8
|
| 89 |
-
},
|
| 90 |
-
"Chemistry": {
|
| 91 |
-
"Average Score": 82.55189735524202,
|
| 92 |
-
"Standard Deviation": null,
|
| 93 |
-
"Rank": 7
|
| 94 |
-
},
|
| 95 |
-
"CPP": {
|
| 96 |
-
"Average Score": 92.43090226400756,
|
| 97 |
-
"Standard Deviation": null,
|
| 98 |
-
"Rank": 2
|
| 99 |
-
}
|
| 100 |
-
}
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"config": {
|
| 104 |
-
"model_name": "gpt-4o-2024-05-13",
|
| 105 |
-
"organization": "OpenAI",
|
| 106 |
-
"license": "Proprietary",
|
| 107 |
-
"knowledge_cutoff": "2023/10"
|
| 108 |
-
},
|
| 109 |
-
"results": {
|
| 110 |
-
"OVERALL": {
|
| 111 |
-
"Average Score": 72.6093654197998,
|
| 112 |
-
"Standard Deviation": 13.515345690976028,
|
| 113 |
-
"Rank": 10
|
| 114 |
-
},
|
| 115 |
-
"Geometry": {
|
| 116 |
-
"Average Score": 0.972472377,
|
| 117 |
-
"Standard Deviation": 0.01648274205,
|
| 118 |
-
"Rank": 4
|
| 119 |
-
},
|
| 120 |
-
"Algebra": {
|
| 121 |
-
"Average Score": 0.995511298,
|
| 122 |
-
"Standard Deviation": 0.004097802515,
|
| 123 |
-
"Rank": 2
|
| 124 |
-
},
|
| 125 |
-
"Probability": {
|
| 126 |
-
"Average Score": 77.97816201050715,
|
| 127 |
-
"Standard Deviation": null,
|
| 128 |
-
"Rank": 8
|
| 129 |
-
},
|
| 130 |
-
"Logical": {
|
| 131 |
-
"Average Score": 75.65058939137873,
|
| 132 |
-
"Standard Deviation": 0.07522785572103825,
|
| 133 |
-
"Rank": 9
|
| 134 |
-
},
|
| 135 |
-
"Social": {
|
| 136 |
-
"Average Score": 0.609875087,
|
| 137 |
-
"Standard Deviation": 0.038729239,
|
| 138 |
-
"Rank": 13
|
| 139 |
-
},
|
| 140 |
-
"Chemistry": {
|
| 141 |
-
"Average Score": 76.03377031297643,
|
| 142 |
-
"Standard Deviation": null,
|
| 143 |
-
"Rank": 9
|
| 144 |
-
},
|
| 145 |
-
"CPP": {
|
| 146 |
-
"Average Score": 79.1592634699295,
|
| 147 |
-
"Standard Deviation": null,
|
| 148 |
-
"Rank": 6
|
| 149 |
-
}
|
| 150 |
-
}
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"config": {
|
| 154 |
-
"model_name": "gpt-4-turbo-2024-04-09",
|
| 155 |
-
"organization": "OpenAI",
|
| 156 |
-
"license": "Proprietary",
|
| 157 |
-
"knowledge_cutoff": "2023/12"
|
| 158 |
-
},
|
| 159 |
-
"results": {
|
| 160 |
-
"OVERALL": {
|
| 161 |
-
"Average Score": 73.32308543749606,
|
| 162 |
-
"Standard Deviation": 6.562777844134629,
|
| 163 |
-
"Rank": 9
|
| 164 |
-
},
|
| 165 |
-
"Geometry": {
|
| 166 |
-
"Average Score": 0.95374588,
|
| 167 |
-
"Standard Deviation": 0.03109307166,
|
| 168 |
-
"Rank": 5
|
| 169 |
-
},
|
| 170 |
-
"Algebra": {
|
| 171 |
-
"Average Score": 0.930945223,
|
| 172 |
-
"Standard Deviation": 0.06705136813,
|
| 173 |
-
"Rank": 4
|
| 174 |
-
},
|
| 175 |
-
"Probability": {
|
| 176 |
-
"Average Score": 74.97144205445957,
|
| 177 |
-
"Standard Deviation": null,
|
| 178 |
-
"Rank": 12
|
| 179 |
-
},
|
| 180 |
-
"Logical": {
|
| 181 |
-
"Average Score": 76.82291715624933,
|
| 182 |
-
"Standard Deviation": 0.03462548327631355,
|
| 183 |
-
"Rank": 7
|
| 184 |
-
},
|
| 185 |
-
"Social": {
|
| 186 |
-
"Average Score": 0.715935163,
|
| 187 |
-
"Standard Deviation": 0.1209141409,
|
| 188 |
-
"Rank": 6
|
| 189 |
-
},
|
| 190 |
-
"Chemistry": {
|
| 191 |
-
"Average Score": 70.44329321394066,
|
| 192 |
-
"Standard Deviation": null,
|
| 193 |
-
"Rank": 12
|
| 194 |
-
},
|
| 195 |
-
"CPP": {
|
| 196 |
-
"Average Score": 70.73143363230263,
|
| 197 |
-
"Standard Deviation": null,
|
| 198 |
-
"Rank": 11
|
| 199 |
-
}
|
| 200 |
-
}
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"config": {
|
| 204 |
-
"model_name": "gemini-1.5-pro-001",
|
| 205 |
-
"organization": "Google",
|
| 206 |
-
"license": "Proprietary",
|
| 207 |
-
"knowledge_cutoff": "2023/11"
|
| 208 |
-
},
|
| 209 |
-
"results": {
|
| 210 |
-
"OVERALL": {
|
| 211 |
-
"Average Score": 74.27365448117855,
|
| 212 |
-
"Standard Deviation": 3.9515447172901847,
|
| 213 |
-
"Rank": 8
|
| 214 |
-
},
|
| 215 |
-
"Geometry": {
|
| 216 |
-
"Average Score": 0.9947169,
|
| 217 |
-
"Standard Deviation": 0.009150597621,
|
| 218 |
-
"Rank": 2
|
| 219 |
-
},
|
| 220 |
-
"Algebra": {
|
| 221 |
-
"Average Score": 0.857464301,
|
| 222 |
-
"Standard Deviation": 0.05014285338,
|
| 223 |
-
"Rank": 5
|
| 224 |
-
},
|
| 225 |
-
"Probability": {
|
| 226 |
-
"Average Score": 64.77713215500482,
|
| 227 |
-
"Standard Deviation": null,
|
| 228 |
-
"Rank": 15
|
| 229 |
-
},
|
| 230 |
-
"Logical": {
|
| 231 |
-
"Average Score": 74.3275461555815,
|
| 232 |
-
"Standard Deviation": 0.8092355737847541,
|
| 233 |
-
"Rank": 10
|
| 234 |
-
},
|
| 235 |
-
"Social": {
|
| 236 |
-
"Average Score": 0.649601885,
|
| 237 |
-
"Standard Deviation": 0.104854889,
|
| 238 |
-
"Rank": 11
|
| 239 |
-
}
|
| 240 |
-
}
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"config": {
|
| 244 |
-
"model_name": "qwen2-72b-instruct",
|
| 245 |
-
"organization": "Alibaba",
|
| 246 |
-
"license": "Qianwen LICENSE",
|
| 247 |
-
"knowledge_cutoff": "2024/09"
|
| 248 |
-
},
|
| 249 |
-
"results": {
|
| 250 |
-
"OVERALL": {
|
| 251 |
-
"Average Score": 71.00423311357184,
|
| 252 |
-
"Standard Deviation": 1.6189609141983887,
|
| 253 |
-
"Rank": 12
|
| 254 |
-
},
|
| 255 |
-
"Geometry": {
|
| 256 |
-
"Average Score": 0.796870305,
|
| 257 |
-
"Standard Deviation": 0.0509025346,
|
| 258 |
-
"Rank": 9
|
| 259 |
-
},
|
| 260 |
-
"Algebra": {
|
| 261 |
-
"Average Score": 0.836194231,
|
| 262 |
-
"Standard Deviation": 0.04517093028,
|
| 263 |
-
"Rank": 6
|
| 264 |
-
},
|
| 265 |
-
"Probability": {
|
| 266 |
-
"Average Score": 76.33751777233937,
|
| 267 |
-
"Standard Deviation": null,
|
| 268 |
-
"Rank": 10
|
| 269 |
-
},
|
| 270 |
-
"Logical": {
|
| 271 |
-
"Average Score": 61.22020517318166,
|
| 272 |
-
"Standard Deviation": 10.241399997578569,
|
| 273 |
-
"Rank": 17
|
| 274 |
-
},
|
| 275 |
-
"Social": {
|
| 276 |
-
"Average Score": 0.652578786,
|
| 277 |
-
"Standard Deviation": 0.04259293171,
|
| 278 |
-
"Rank": 10
|
| 279 |
-
},
|
| 280 |
-
"Chemistry": {
|
| 281 |
-
"Average Score": 70.44342338869497,
|
| 282 |
-
"Standard Deviation": null,
|
| 283 |
-
"Rank": 12
|
| 284 |
-
},
|
| 285 |
-
"CPP": {
|
| 286 |
-
"Average Score": 73.54037778797029,
|
| 287 |
-
"Standard Deviation": null,
|
| 288 |
-
"Rank": 7
|
| 289 |
-
}
|
| 290 |
-
}
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"config": {
|
| 294 |
-
"model_name": "gpt-4o-mini-2024-07-18",
|
| 295 |
-
"organization": "OpenAI",
|
| 296 |
-
"license": "Proprietary",
|
| 297 |
-
"knowledge_cutoff": "2023/10"
|
| 298 |
-
},
|
| 299 |
-
"results": {
|
| 300 |
-
"OVERALL": {
|
| 301 |
-
"Average Score": 77.35427394420829,
|
| 302 |
-
"Standard Deviation": 3.162321541714492,
|
| 303 |
-
"Rank": 6
|
| 304 |
-
},
|
| 305 |
-
"Geometry": {
|
| 306 |
-
"Average Score": 0.946650435,
|
| 307 |
-
"Standard Deviation": 0.01831236482,
|
| 308 |
-
"Rank": 7
|
| 309 |
-
},
|
| 310 |
-
"Algebra": {
|
| 311 |
-
"Average Score": 0.796243022,
|
| 312 |
-
"Standard Deviation": 0.05537539202,
|
| 313 |
-
"Rank": 7
|
| 314 |
-
},
|
| 315 |
-
"Probability": {
|
| 316 |
-
"Average Score": 77.63972720989734,
|
| 317 |
-
"Standard Deviation": null,
|
| 318 |
-
"Rank": 9
|
| 319 |
-
},
|
| 320 |
-
"Logical": {
|
| 321 |
-
"Average Score": 71.81267717239906,
|
| 322 |
-
"Standard Deviation": 0.3393593163824375,
|
| 323 |
-
"Rank": 11
|
| 324 |
-
},
|
| 325 |
-
"Social": {
|
| 326 |
-
"Average Score": 0.691949855,
|
| 327 |
-
"Standard Deviation": 0.02072934333,
|
| 328 |
-
"Rank": 7
|
| 329 |
-
},
|
| 330 |
-
"Chemistry": {
|
| 331 |
-
"Average Score": 78.10636943659426,
|
| 332 |
-
"Standard Deviation": null,
|
| 333 |
-
"Rank": 8
|
| 334 |
-
},
|
| 335 |
-
"CPP": {
|
| 336 |
-
"Average Score": 88.3877070580296,
|
| 337 |
-
"Standard Deviation": null,
|
| 338 |
-
"Rank": 3
|
| 339 |
-
}
|
| 340 |
-
}
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"config": {
|
| 344 |
-
"model_name": "claude-3.5-sonnet",
|
| 345 |
-
"organization": "Anthropic",
|
| 346 |
-
"license": "Proprietary",
|
| 347 |
-
"knowledge_cutoff": "2024/04"
|
| 348 |
-
},
|
| 349 |
-
"results": {
|
| 350 |
-
"OVERALL": {
|
| 351 |
-
"Average Score": 75.97534774560863,
|
| 352 |
-
"Standard Deviation": 9.237316832705584,
|
| 353 |
-
"Rank": 7
|
| 354 |
-
},
|
| 355 |
-
"Geometry": {
|
| 356 |
-
"Average Score": 0.95316419,
|
| 357 |
-
"Standard Deviation": 0.02081192856,
|
| 358 |
-
"Rank": 6
|
| 359 |
-
},
|
| 360 |
-
"Algebra": {
|
| 361 |
-
"Average Score": 0.759789952,
|
| 362 |
-
"Standard Deviation": 0.02611765096,
|
| 363 |
-
"Rank": 8
|
| 364 |
-
},
|
| 365 |
-
"Probability": {
|
| 366 |
-
"Average Score": 65.4531881044298,
|
| 367 |
-
"Standard Deviation": null,
|
| 368 |
-
"Rank": 14
|
| 369 |
-
},
|
| 370 |
-
"Logical": {
|
| 371 |
-
"Average Score": 76.47424588300288,
|
| 372 |
-
"Standard Deviation": 0.07699328617321737,
|
| 373 |
-
"Rank": 8
|
| 374 |
-
},
|
| 375 |
-
"Social": {
|
| 376 |
-
"Average Score": 0.790002247,
|
| 377 |
-
"Standard Deviation": 0.1007410022,
|
| 378 |
-
"Rank": 4
|
| 379 |
-
},
|
| 380 |
-
"Chemistry": {
|
| 381 |
-
"Average Score": 85.17654674052096,
|
| 382 |
-
"Standard Deviation": null,
|
| 383 |
-
"Rank": 6
|
| 384 |
-
},
|
| 385 |
-
"CPP": {
|
| 386 |
-
"Average Score": 82.37734076815008,
|
| 387 |
-
"Standard Deviation": null,
|
| 388 |
-
"Rank": 5
|
| 389 |
-
}
|
| 390 |
-
}
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"config": {
|
| 394 |
-
"model_name": "o1-mini",
|
| 395 |
-
"organization": "OpenAI",
|
| 396 |
-
"license": "Proprietary",
|
| 397 |
-
"knowledge_cutoff": "2023/10"
|
| 398 |
-
},
|
| 399 |
-
"results": {
|
| 400 |
-
"OVERALL": {
|
| 401 |
-
"Average Score": 87.92989248183513,
|
| 402 |
-
"Standard Deviation": 1.3401058431409953,
|
| 403 |
-
"Rank": 2
|
| 404 |
-
},
|
| 405 |
-
"Geometry": {
|
| 406 |
-
"Average Score": "N/A",
|
| 407 |
-
"Standard Deviation": "N/A",
|
| 408 |
-
"Rank": "N/A"
|
| 409 |
-
},
|
| 410 |
-
"Algebra": {
|
| 411 |
-
"Average Score": "N/A",
|
| 412 |
-
"Standard Deviation": "N/A",
|
| 413 |
-
"Rank": "N/A"
|
| 414 |
-
},
|
| 415 |
-
"Probability": {
|
| 416 |
-
"Average Score": 100.0,
|
| 417 |
-
"Standard Deviation": null,
|
| 418 |
-
"Rank": 1
|
| 419 |
-
},
|
| 420 |
-
"Logical": {
|
| 421 |
-
"Average Score": 99.15920225407733,
|
| 422 |
-
"Standard Deviation": 0.49801294410288666,
|
| 423 |
-
"Rank": 2
|
| 424 |
-
},
|
| 425 |
-
"Social": {
|
| 426 |
-
"Average Score": 0.993974241,
|
| 427 |
-
"Standard Deviation": 0.001996882328,
|
| 428 |
-
"Rank": 2
|
| 429 |
-
}
|
| 430 |
-
}
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"config": {
|
| 434 |
-
"model_name": "o1-preview",
|
| 435 |
-
"organization": "OpenAI",
|
| 436 |
-
"license": "Proprietary",
|
| 437 |
-
"knowledge_cutoff": "2023/10"
|
| 438 |
-
},
|
| 439 |
-
"results": {
|
| 440 |
-
"OVERALL": {
|
| 441 |
-
"Average Score": 85.40247108906188,
|
| 442 |
-
"Standard Deviation": 1.5796898764998464,
|
| 443 |
-
"Rank": 4
|
| 444 |
-
},
|
| 445 |
-
"Geometry": {
|
| 446 |
-
"Average Score": "N/A",
|
| 447 |
-
"Standard Deviation": "N/A",
|
| 448 |
-
"Rank": "N/A"
|
| 449 |
-
},
|
| 450 |
-
"Algebra": {
|
| 451 |
-
"Average Score": "N/A",
|
| 452 |
-
"Standard Deviation": "N/A",
|
| 453 |
-
"Rank": "N/A"
|
| 454 |
-
},
|
| 455 |
-
"Probability": {
|
| 456 |
-
"Average Score": 90.32625019320989,
|
| 457 |
-
"Standard Deviation": null,
|
| 458 |
-
"Rank": 5
|
| 459 |
-
},
|
| 460 |
-
"Logical": {
|
| 461 |
-
"Average Score": 98.18241651273537,
|
| 462 |
-
"Standard Deviation": 0.16231417987288874,
|
| 463 |
-
"Rank": 4
|
| 464 |
-
},
|
| 465 |
-
"Social": {
|
| 466 |
-
"Average Score": 1.0,
|
| 467 |
-
"Standard Deviation": 0.0,
|
| 468 |
-
"Rank": 1
|
| 469 |
-
}
|
| 470 |
-
}
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"config": {
|
| 474 |
-
"model_name": "gemini-1.5-flash-001",
|
| 475 |
-
"organization": "Google",
|
| 476 |
-
"license": "Proprietary",
|
| 477 |
-
"knowledge_cutoff": "2023/11"
|
| 478 |
-
},
|
| 479 |
-
"results": {
|
| 480 |
-
"OVERALL": {
|
| 481 |
-
"Average Score": 67.67997467963976,
|
| 482 |
-
"Standard Deviation": 2.624276751646549,
|
| 483 |
-
"Rank": 13
|
| 484 |
-
},
|
| 485 |
-
"Geometry": {
|
| 486 |
-
"Average Score": 0.804144103,
|
| 487 |
-
"Standard Deviation": 0.1327142178,
|
| 488 |
-
"Rank": 8
|
| 489 |
-
},
|
| 490 |
-
"Algebra": {
|
| 491 |
-
"Average Score": 0.731776765,
|
| 492 |
-
"Standard Deviation": 0.02594657111,
|
| 493 |
-
"Rank": 9
|
| 494 |
-
},
|
| 495 |
-
"Probability": {
|
| 496 |
-
"Average Score": 61.17190439316032,
|
| 497 |
-
"Standard Deviation": null,
|
| 498 |
-
"Rank": 19
|
| 499 |
-
},
|
| 500 |
-
"Logical": {
|
| 501 |
-
"Average Score": 62.284381466778335,
|
| 502 |
-
"Standard Deviation": 3.9592476945909674,
|
| 503 |
-
"Rank": 16
|
| 504 |
-
},
|
| 505 |
-
"Social": {
|
| 506 |
-
"Average Score": 0.555933822,
|
| 507 |
-
"Standard Deviation": 0.1029934524,
|
| 508 |
-
"Rank": 15
|
| 509 |
-
},
|
| 510 |
-
"Chemistry": {
|
| 511 |
-
"Average Score": 70.24726462490831,
|
| 512 |
-
"Standard Deviation": null,
|
| 513 |
-
"Rank": 15
|
| 514 |
-
},
|
| 515 |
-
"CPP": {
|
| 516 |
-
"Average Score": 72.1127762005651,
|
| 517 |
-
"Standard Deviation": null,
|
| 518 |
-
"Rank": 10
|
| 519 |
-
}
|
| 520 |
-
}
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"config": {
|
| 524 |
-
"model_name": "gpt4-1106",
|
| 525 |
-
"organization": "OpenAI",
|
| 526 |
-
"license": "Proprietary",
|
| 527 |
-
"knowledge_cutoff": "2024/04"
|
| 528 |
-
},
|
| 529 |
-
"results": {
|
| 530 |
-
"OVERALL": {
|
| 531 |
-
"Average Score": 72.24829405851214,
|
| 532 |
-
"Standard Deviation": 13.633826990442946,
|
| 533 |
-
"Rank": 11
|
| 534 |
-
},
|
| 535 |
-
"Geometry": {
|
| 536 |
-
"Average Score": 0.71843088,
|
| 537 |
-
"Standard Deviation": 0.04778038294,
|
| 538 |
-
"Rank": 11
|
| 539 |
-
},
|
| 540 |
-
"Algebra": {
|
| 541 |
-
"Average Score": 0.712910417,
|
| 542 |
-
"Standard Deviation": 0.02581828898,
|
| 543 |
-
"Rank": 10
|
| 544 |
-
},
|
| 545 |
-
"Probability": {
|
| 546 |
-
"Average Score": 63.29462909293814,
|
| 547 |
-
"Standard Deviation": null,
|
| 548 |
-
"Rank": 16
|
| 549 |
-
},
|
| 550 |
-
"Logical": {
|
| 551 |
-
"Average Score": 62.987098158883875,
|
| 552 |
-
"Standard Deviation": 4.027795425350514,
|
| 553 |
-
"Rank": 15
|
| 554 |
-
},
|
| 555 |
-
"Social": {
|
| 556 |
-
"Average Score": 0.450609816,
|
| 557 |
-
"Standard Deviation": 0.05208655446,
|
| 558 |
-
"Rank": 21
|
| 559 |
-
},
|
| 560 |
-
"Chemistry": {
|
| 561 |
-
"Average Score": 67.34047237109209,
|
| 562 |
-
"Standard Deviation": null,
|
| 563 |
-
"Rank": 16
|
| 564 |
-
},
|
| 565 |
-
"CPP": {
|
| 566 |
-
"Average Score": 69.11824072252848,
|
| 567 |
-
"Standard Deviation": null,
|
| 568 |
-
"Rank": 12
|
| 569 |
-
}
|
| 570 |
-
}
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"config": {
|
| 574 |
-
"model_name": "gemma-2-27b-it",
|
| 575 |
-
"organization": "Google",
|
| 576 |
-
"license": "Gemma License",
|
| 577 |
-
"knowledge_cutoff": "2024/06"
|
| 578 |
-
},
|
| 579 |
-
"results": {
|
| 580 |
-
"OVERALL": {
|
| 581 |
-
"Average Score": 62.70975283121063,
|
| 582 |
-
"Standard Deviation": 6.376450054715319,
|
| 583 |
-
"Rank": 15
|
| 584 |
-
},
|
| 585 |
-
"Geometry": {
|
| 586 |
-
"Average Score": 0.60112744,
|
| 587 |
-
"Standard Deviation": 0.0469109952,
|
| 588 |
-
"Rank": 17
|
| 589 |
-
},
|
| 590 |
-
"Algebra": {
|
| 591 |
-
"Average Score": 0.687955914,
|
| 592 |
-
"Standard Deviation": 0.01959958192,
|
| 593 |
-
"Rank": 11
|
| 594 |
-
},
|
| 595 |
-
"Probability": {
|
| 596 |
-
"Average Score": 60.04180799425261,
|
| 597 |
-
"Standard Deviation": null,
|
| 598 |
-
"Rank": 20
|
| 599 |
-
},
|
| 600 |
-
"Logical": {
|
| 601 |
-
"Average Score": 60.77082327163094,
|
| 602 |
-
"Standard Deviation": 7.2164902432618625,
|
| 603 |
-
"Rank": 19
|
| 604 |
-
},
|
| 605 |
-
"Social": {
|
| 606 |
-
"Average Score": 0.487844257,
|
| 607 |
-
"Standard Deviation": 0.05857760809,
|
| 608 |
-
"Rank": 18
|
| 609 |
-
},
|
| 610 |
-
"Chemistry": {
|
| 611 |
-
"Average Score": 61.68181926111706,
|
| 612 |
-
"Standard Deviation": null,
|
| 613 |
-
"Rank": 18
|
| 614 |
-
},
|
| 615 |
-
"CPP": {
|
| 616 |
-
"Average Score": 63.28920072143611,
|
| 617 |
-
"Standard Deviation": null,
|
| 618 |
-
"Rank": 14
|
| 619 |
-
}
|
| 620 |
-
}
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"config": {
|
| 624 |
-
"model_name": "claude-3-opus",
|
| 625 |
-
"organization": "Anthropic",
|
| 626 |
-
"license": "Proprietary",
|
| 627 |
-
"knowledge_cutoff": "2023/08"
|
| 628 |
-
},
|
| 629 |
-
"results": {
|
| 630 |
-
"OVERALL": {
|
| 631 |
-
"Average Score": 60.56449573632771,
|
| 632 |
-
"Standard Deviation": 8.485936885427277,
|
| 633 |
-
"Rank": 17
|
| 634 |
-
},
|
| 635 |
-
"Geometry": {
|
| 636 |
-
"Average Score": 0.7215743,
|
| 637 |
-
"Standard Deviation": 0.04712598358,
|
| 638 |
-
"Rank": 10
|
| 639 |
-
},
|
| 640 |
-
"Algebra": {
|
| 641 |
-
"Average Score": 0.68777327,
|
| 642 |
-
"Standard Deviation": 0.02382683713,
|
| 643 |
-
"Rank": 12
|
| 644 |
-
},
|
| 645 |
-
"Probability": {
|
| 646 |
-
"Average Score": 62.296041016641176,
|
| 647 |
-
"Standard Deviation": null,
|
| 648 |
-
"Rank": 17
|
| 649 |
-
},
|
| 650 |
-
"Logical": {
|
| 651 |
-
"Average Score": 68.36295609287292,
|
| 652 |
-
"Standard Deviation": 1.6558271236588655,
|
| 653 |
-
"Rank": 13
|
| 654 |
-
},
|
| 655 |
-
"Social": {
|
| 656 |
-
"Average Score": 0.663410854,
|
| 657 |
-
"Standard Deviation": 0.09540220876,
|
| 658 |
-
"Rank": 9
|
| 659 |
-
},
|
| 660 |
-
"Chemistry": {
|
| 661 |
-
"Average Score": 70.44337273504232,
|
| 662 |
-
"Standard Deviation": null,
|
| 663 |
-
"Rank": 12
|
| 664 |
-
},
|
| 665 |
-
"CPP": {
|
| 666 |
-
"Average Score": 73.5404403567132,
|
| 667 |
-
"Standard Deviation": null,
|
| 668 |
-
"Rank": 8
|
| 669 |
-
}
|
| 670 |
-
}
|
| 671 |
-
},
|
| 672 |
-
{
|
| 673 |
-
"config": {
|
| 674 |
-
"model_name": "gemma-2-9b-it-simpo",
|
| 675 |
-
"organization": "Google",
|
| 676 |
-
"license": "Gemma License",
|
| 677 |
-
"knowledge_cutoff": "2024/07"
|
| 678 |
-
},
|
| 679 |
-
"results": {
|
| 680 |
-
"OVERALL": {
|
| 681 |
-
"Average Score": "N/A",
|
| 682 |
-
"Standard Deviation": "N/A",
|
| 683 |
-
"Rank": "N/A"
|
| 684 |
-
},
|
| 685 |
-
"Geometry": {
|
| 686 |
-
"Average Score": 0.582787508,
|
| 687 |
-
"Standard Deviation": 0.03965204074,
|
| 688 |
-
"Rank": 18
|
| 689 |
-
},
|
| 690 |
-
"Algebra": {
|
| 691 |
-
"Average Score": 0.658648133,
|
| 692 |
-
"Standard Deviation": 0.02565919856,
|
| 693 |
-
"Rank": 13
|
| 694 |
-
},
|
| 695 |
-
"Probability": {
|
| 696 |
-
"Average Score": 57.545408188912894,
|
| 697 |
-
"Standard Deviation": null,
|
| 698 |
-
"Rank": 23
|
| 699 |
-
},
|
| 700 |
-
"Logical": {
|
| 701 |
-
"Average Score": 53.1996479262466,
|
| 702 |
-
"Standard Deviation": 2.690106544431167,
|
| 703 |
-
"Rank": 23
|
| 704 |
-
},
|
| 705 |
-
"Social": {
|
| 706 |
-
"Average Score": 0.635266187,
|
| 707 |
-
"Standard Deviation": 0.03620021751,
|
| 708 |
-
"Rank": 12
|
| 709 |
-
},
|
| 710 |
-
"Chemistry": {
|
| 711 |
-
"Average Score": 74.44267231381626,
|
| 712 |
-
"Standard Deviation": null,
|
| 713 |
-
"Rank": 11
|
| 714 |
-
},
|
| 715 |
-
"CPP": {
|
| 716 |
-
"Average Score": 73.43757596214863,
|
| 717 |
-
"Standard Deviation": null,
|
| 718 |
-
"Rank": 9
|
| 719 |
-
}
|
| 720 |
-
}
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"config": {
|
| 724 |
-
"model_name": "qwen1.5-72b-chat",
|
| 725 |
-
"organization": "Alibaba",
|
| 726 |
-
"license": "Qianwen LICENSE",
|
| 727 |
-
"knowledge_cutoff": "2024/03"
|
| 728 |
-
},
|
| 729 |
-
"results": {
|
| 730 |
-
"OVERALL": {
|
| 731 |
-
"Average Score": 52.983715751652085,
|
| 732 |
-
"Standard Deviation": 3.097613966427763,
|
| 733 |
-
"Rank": 18
|
| 734 |
-
},
|
| 735 |
-
"Geometry": {
|
| 736 |
-
"Average Score": 0.543139301,
|
| 737 |
-
"Standard Deviation": 0.03425202326,
|
| 738 |
-
"Rank": 22
|
| 739 |
-
},
|
| 740 |
-
"Algebra": {
|
| 741 |
-
"Average Score": 0.635228729,
|
| 742 |
-
"Standard Deviation": 0.01944043425,
|
| 743 |
-
"Rank": 14
|
| 744 |
-
},
|
| 745 |
-
"Probability": {
|
| 746 |
-
"Average Score": 52.650033879924905,
|
| 747 |
-
"Standard Deviation": null,
|
| 748 |
-
"Rank": 26
|
| 749 |
-
},
|
| 750 |
-
"Logical": {
|
| 751 |
-
"Average Score": 32.628853250402074,
|
| 752 |
-
"Standard Deviation": 3.227745519436025,
|
| 753 |
-
"Rank": 37
|
| 754 |
-
},
|
| 755 |
-
"Social": {
|
| 756 |
-
"Average Score": 0.415007627,
|
| 757 |
-
"Standard Deviation": 0.03920053159,
|
| 758 |
-
"Rank": 22
|
| 759 |
-
},
|
| 760 |
-
"Chemistry": {
|
| 761 |
-
"Average Score": 47.5126781973184,
|
| 762 |
-
"Standard Deviation": null,
|
| 763 |
-
"Rank": 24
|
| 764 |
-
},
|
| 765 |
-
"CPP": {
|
| 766 |
-
"Average Score": 48.69302376665551,
|
| 767 |
-
"Standard Deviation": null,
|
| 768 |
-
"Rank": 20
|
| 769 |
-
}
|
| 770 |
-
}
|
| 771 |
-
},
|
| 772 |
-
{
|
| 773 |
-
"config": {
|
| 774 |
-
"model_name": "qwen1.5-32b-chat",
|
| 775 |
-
"organization": "Alibaba",
|
| 776 |
-
"license": "Qianwen LICENSE",
|
| 777 |
-
"knowledge_cutoff": "2024/03"
|
| 778 |
-
},
|
| 779 |
-
"results": {
|
| 780 |
-
"OVERALL": {
|
| 781 |
-
"Average Score": 26.978561942890224,
|
| 782 |
-
"Standard Deviation": 1.575986887925592,
|
| 783 |
-
"Rank": 32
|
| 784 |
-
},
|
| 785 |
-
"Geometry": {
|
| 786 |
-
"Average Score": 0.51086835,
|
| 787 |
-
"Standard Deviation": 0.04052471998,
|
| 788 |
-
"Rank": 25
|
| 789 |
-
},
|
| 790 |
-
"Algebra": {
|
| 791 |
-
"Average Score": 0.609003168,
|
| 792 |
-
"Standard Deviation": 0.04874143541,
|
| 793 |
-
"Rank": 15
|
| 794 |
-
},
|
| 795 |
-
"Probability": {
|
| 796 |
-
"Average Score": 49.50617919486678,
|
| 797 |
-
"Standard Deviation": null,
|
| 798 |
-
"Rank": 29
|
| 799 |
-
},
|
| 800 |
-
"Logical": {
|
| 801 |
-
"Average Score": 34.07387941414556,
|
| 802 |
-
"Standard Deviation": 4.616974831074921,
|
| 803 |
-
"Rank": 34
|
| 804 |
-
},
|
| 805 |
-
"Social": {
|
| 806 |
-
"Average Score": 0.380987334,
|
| 807 |
-
"Standard Deviation": 0.03762251776,
|
| 808 |
-
"Rank": 24
|
| 809 |
-
},
|
| 810 |
-
"Chemistry": {
|
| 811 |
-
"Average Score": 44.06627265183811,
|
| 812 |
-
"Standard Deviation": null,
|
| 813 |
-
"Rank": 28
|
| 814 |
-
},
|
| 815 |
-
"CPP": {
|
| 816 |
-
"Average Score": 45.14284028264288,
|
| 817 |
-
"Standard Deviation": null,
|
| 818 |
-
"Rank": 24
|
| 819 |
-
}
|
| 820 |
-
}
|
| 821 |
-
},
|
| 822 |
-
{
|
| 823 |
-
"config": {
|
| 824 |
-
"model_name": "google-gemma-2-9b-it",
|
| 825 |
-
"organization": "Google",
|
| 826 |
-
"license": "Proprietary",
|
| 827 |
-
"knowledge_cutoff": "2024/06"
|
| 828 |
-
},
|
| 829 |
-
"results": {
|
| 830 |
-
"OVERALL": {
|
| 831 |
-
"Average Score": 52.23013018580635,
|
| 832 |
-
"Standard Deviation": 3.3939236141078495,
|
| 833 |
-
"Rank": 19
|
| 834 |
-
},
|
| 835 |
-
"Geometry": {
|
| 836 |
-
"Average Score": 0.575371308,
|
| 837 |
-
"Standard Deviation": 0.03556220251,
|
| 838 |
-
"Rank": 20
|
| 839 |
-
},
|
| 840 |
-
"Algebra": {
|
| 841 |
-
"Average Score": 0.597045661,
|
| 842 |
-
"Standard Deviation": 0.0313828123,
|
| 843 |
-
"Rank": 16
|
| 844 |
-
},
|
| 845 |
-
"Probability": {
|
| 846 |
-
"Average Score": 58.73062101843859,
|
| 847 |
-
"Standard Deviation": null,
|
| 848 |
-
"Rank": 21
|
| 849 |
-
},
|
| 850 |
-
"Logical": {
|
| 851 |
-
"Average Score": 58.01791397899675,
|
| 852 |
-
"Standard Deviation": 5.751983660134971,
|
| 853 |
-
"Rank": 21
|
| 854 |
-
},
|
| 855 |
-
"Social": {
|
| 856 |
-
"Average Score": 0.768337958,
|
| 857 |
-
"Standard Deviation": 0.04078610476,
|
| 858 |
-
"Rank": 5
|
| 859 |
-
},
|
| 860 |
-
"Chemistry": {
|
| 861 |
-
"Average Score": 52.69494515004607,
|
| 862 |
-
"Standard Deviation": null,
|
| 863 |
-
"Rank": 21
|
| 864 |
-
},
|
| 865 |
-
"CPP": {
|
| 866 |
-
"Average Score": 54.03167523687635,
|
| 867 |
-
"Standard Deviation": null,
|
| 868 |
-
"Rank": 17
|
| 869 |
-
}
|
| 870 |
-
}
|
| 871 |
-
},
|
| 872 |
-
{
|
| 873 |
-
"config": {
|
| 874 |
-
"model_name": "yi-1.5-34b-chat",
|
| 875 |
-
"organization": "01 AI",
|
| 876 |
-
"license": "Proprietary",
|
| 877 |
-
"knowledge_cutoff": "2024/05"
|
| 878 |
-
},
|
| 879 |
-
"results": {
|
| 880 |
-
"OVERALL": {
|
| 881 |
-
"Average Score": 62.568637878216464,
|
| 882 |
-
"Standard Deviation": 8.554205798418673,
|
| 883 |
-
"Rank": 16
|
| 884 |
-
},
|
| 885 |
-
"Geometry": {
|
| 886 |
-
"Average Score": 0.566666724,
|
| 887 |
-
"Standard Deviation": 0.04001381658,
|
| 888 |
-
"Rank": 21
|
| 889 |
-
},
|
| 890 |
-
"Algebra": {
|
| 891 |
-
"Average Score": 0.590997292,
|
| 892 |
-
"Standard Deviation": 0.03594087315,
|
| 893 |
-
"Rank": 17
|
| 894 |
-
},
|
| 895 |
-
"Probability": {
|
| 896 |
-
"Average Score": 57.545207891104354,
|
| 897 |
-
"Standard Deviation": null,
|
| 898 |
-
"Rank": 22
|
| 899 |
-
},
|
| 900 |
-
"Logical": {
|
| 901 |
-
"Average Score": 56.598158131627194,
|
| 902 |
-
"Standard Deviation": 1.1072821075127297,
|
| 903 |
-
"Rank": 22
|
| 904 |
-
},
|
| 905 |
-
"Social": {
|
| 906 |
-
"Average Score": 0.516980832,
|
| 907 |
-
"Standard Deviation": 0.03369347985,
|
| 908 |
-
"Rank": 17
|
| 909 |
-
},
|
| 910 |
-
"Chemistry": {
|
| 911 |
-
"Average Score": 50.867343712131174,
|
| 912 |
-
"Standard Deviation": null,
|
| 913 |
-
"Rank": 22
|
| 914 |
-
},
|
| 915 |
-
"CPP": {
|
| 916 |
-
"Average Score": 52.148798061768964,
|
| 917 |
-
"Standard Deviation": null,
|
| 918 |
-
"Rank": 18
|
| 919 |
-
}
|
| 920 |
-
}
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"config": {
|
| 924 |
-
"model_name": "meta-llama-3.1-70b-instruct",
|
| 925 |
-
"organization": "Meta",
|
| 926 |
-
"license": "Llama 3.1 Community",
|
| 927 |
-
"knowledge_cutoff": "2023/12"
|
| 928 |
-
},
|
| 929 |
-
"results": {
|
| 930 |
-
"OVERALL": {
|
| 931 |
-
"Average Score": 65.61302047306724,
|
| 932 |
-
"Standard Deviation": 7.113338386318571,
|
| 933 |
-
"Rank": 14
|
| 934 |
-
},
|
| 935 |
-
"Geometry": {
|
| 936 |
-
"Average Score": 0.76184398,
|
| 937 |
-
"Standard Deviation": 0.01790377984,
|
| 938 |
-
"Rank": 10
|
| 939 |
-
},
|
| 940 |
-
"Algebra": {
|
| 941 |
-
"Average Score": 0.732041699,
|
| 942 |
-
"Standard Deviation": 0.02621439062,
|
| 943 |
-
"Rank": 9
|
| 944 |
-
},
|
| 945 |
-
"Probability": {
|
| 946 |
-
"Average Score": 65.4531285887158,
|
| 947 |
-
"Standard Deviation": null,
|
| 948 |
-
"Rank": 13
|
| 949 |
-
},
|
| 950 |
-
"Logical": {
|
| 951 |
-
"Average Score": 61.16321386785366,
|
| 952 |
-
"Standard Deviation": 0.8920966760646541,
|
| 953 |
-
"Rank": 18
|
| 954 |
-
},
|
| 955 |
-
"Social": {
|
| 956 |
-
"Average Score": 0.45872939,
|
| 957 |
-
"Standard Deviation": 0.05347039576,
|
| 958 |
-
"Rank": 20
|
| 959 |
-
},
|
| 960 |
-
"Chemistry": {
|
| 961 |
-
"Average Score": 76.03374498429748,
|
| 962 |
-
"Standard Deviation": null,
|
| 963 |
-
"Rank": 9
|
| 964 |
-
},
|
| 965 |
-
"CPP": {
|
| 966 |
-
"Average Score": 84.36815192532764,
|
| 967 |
-
"Standard Deviation": null,
|
| 968 |
-
"Rank": 4
|
| 969 |
-
}
|
| 970 |
-
}
|
| 971 |
-
},
|
| 972 |
-
{
|
| 973 |
-
"config": {
|
| 974 |
-
"model_name": "meta-llama-3.1-8b-instruct",
|
| 975 |
-
"organization": "Meta",
|
| 976 |
-
"license": "Llama 3.1 Community",
|
| 977 |
-
"knowledge_cutoff": "2023/12"
|
| 978 |
-
},
|
| 979 |
-
"results": {
|
| 980 |
-
"OVERALL": {
|
| 981 |
-
"Average Score": 48.86242501618216,
|
| 982 |
-
"Standard Deviation": 3.7761459978540257,
|
| 983 |
-
"Rank": 21
|
| 984 |
-
},
|
| 985 |
-
"Geometry": {
|
| 986 |
-
"Average Score": 0.522442162,
|
| 987 |
-
"Standard Deviation": 0.03908236317,
|
| 988 |
-
"Rank": 23
|
| 989 |
-
},
|
| 990 |
-
"Algebra": {
|
| 991 |
-
"Average Score": 0.582702645,
|
| 992 |
-
"Standard Deviation": 0.05002277711,
|
| 993 |
-
"Rank": 18
|
| 994 |
-
},
|
| 995 |
-
"Probability": {
|
| 996 |
-
"Average Score": 52.44179989233465,
|
| 997 |
-
"Standard Deviation": null,
|
| 998 |
-
"Rank": 27
|
| 999 |
-
},
|
| 1000 |
-
"Logical": {
|
| 1001 |
-
"Average Score": 43.3706774850582,
|
| 1002 |
-
"Standard Deviation": 2.820707319899787,
|
| 1003 |
-
"Rank": 28
|
| 1004 |
-
},
|
| 1005 |
-
"Social": {
|
| 1006 |
-
"Average Score": 0.329195941,
|
| 1007 |
-
"Standard Deviation": 0.03925019528,
|
| 1008 |
-
"Rank": 28
|
| 1009 |
-
},
|
| 1010 |
-
"Chemistry": {
|
| 1011 |
-
"Average Score": 43.36264580455019,
|
| 1012 |
-
"Standard Deviation": null,
|
| 1013 |
-
"Rank": 30
|
| 1014 |
-
},
|
| 1015 |
-
"CPP": {
|
| 1016 |
-
"Average Score": 44.41846841004584,
|
| 1017 |
-
"Standard Deviation": null,
|
| 1018 |
-
"Rank": 26
|
| 1019 |
-
}
|
| 1020 |
-
}
|
| 1021 |
-
},
|
| 1022 |
-
{
|
| 1023 |
-
"config": {
|
| 1024 |
-
"model_name": "gpt3.5-turbo-0125",
|
| 1025 |
-
"organization": "OpenAI",
|
| 1026 |
-
"license": "Proprietary",
|
| 1027 |
-
"knowledge_cutoff": "2021/09"
|
| 1028 |
-
},
|
| 1029 |
-
"results": {
|
| 1030 |
-
"OVERALL": {
|
| 1031 |
-
"Average Score": 18.951737690142235,
|
| 1032 |
-
"Standard Deviation": 0.7967088395458379,
|
| 1033 |
-
"Rank": 42
|
| 1034 |
-
},
|
| 1035 |
-
"Geometry": {
|
| 1036 |
-
"Average Score": 0.678714519,
|
| 1037 |
-
"Standard Deviation": 0.05926546762,
|
| 1038 |
-
"Rank": 12
|
| 1039 |
-
},
|
| 1040 |
-
"Algebra": {
|
| 1041 |
-
"Average Score": 0.569296173,
|
| 1042 |
-
"Standard Deviation": 0.05277281097,
|
| 1043 |
-
"Rank": 19
|
| 1044 |
-
},
|
| 1045 |
-
"Probability": {
|
| 1046 |
-
"Average Score": 45.77959177088119,
|
| 1047 |
-
"Standard Deviation": null,
|
| 1048 |
-
"Rank": 30
|
| 1049 |
-
},
|
| 1050 |
-
"Logical": {
|
| 1051 |
-
"Average Score": 17.159084771200394,
|
| 1052 |
-
"Standard Deviation": 2.5845422782742546,
|
| 1053 |
-
"Rank": 48
|
| 1054 |
-
},
|
| 1055 |
-
"Social": {
|
| 1056 |
-
"Average Score": 0.235071541,
|
| 1057 |
-
"Standard Deviation": 0.02632892457,
|
| 1058 |
-
"Rank": 37
|
| 1059 |
-
},
|
| 1060 |
-
"Chemistry": {
|
| 1061 |
-
"Average Score": 39.52885225927276,
|
| 1062 |
-
"Standard Deviation": null,
|
| 1063 |
-
"Rank": 33
|
| 1064 |
-
},
|
| 1065 |
-
"CPP": {
|
| 1066 |
-
"Average Score": 40.46958736582551,
|
| 1067 |
-
"Standard Deviation": null,
|
| 1068 |
-
"Rank": 29
|
| 1069 |
-
}
|
| 1070 |
-
}
|
| 1071 |
-
},
|
| 1072 |
-
{
|
| 1073 |
-
"config": {
|
| 1074 |
-
"model_name": "llama-3-70b-instruct",
|
| 1075 |
-
"organization": "Meta",
|
| 1076 |
-
"license": "Llama 3 Community",
|
| 1077 |
-
"knowledge_cutoff": "2023/12"
|
| 1078 |
-
},
|
| 1079 |
-
"results": {
|
| 1080 |
-
"OVERALL": {
|
| 1081 |
-
"Average Score": 40.57810915454436,
|
| 1082 |
-
"Standard Deviation": 1.3134243733127455,
|
| 1083 |
-
"Rank": 26
|
| 1084 |
-
},
|
| 1085 |
-
"Geometry": {
|
| 1086 |
-
"Average Score": 0.516865529,
|
| 1087 |
-
"Standard Deviation": 0.03858112564,
|
| 1088 |
-
"Rank": 24
|
| 1089 |
-
},
|
| 1090 |
-
"Algebra": {
|
| 1091 |
-
"Average Score": 0.566756531,
|
| 1092 |
-
"Standard Deviation": 0.03369826926,
|
| 1093 |
-
"Rank": 20
|
| 1094 |
-
},
|
| 1095 |
-
"Probability": {
|
| 1096 |
-
"Average Score": 52.64997876875813,
|
| 1097 |
-
"Standard Deviation": null,
|
| 1098 |
-
"Rank": 25
|
| 1099 |
-
},
|
| 1100 |
-
"Logical": {
|
| 1101 |
-
"Average Score": 70.51651844158742,
|
| 1102 |
-
"Standard Deviation": 0.12355022869457871,
|
| 1103 |
-
"Rank": 12
|
| 1104 |
-
},
|
| 1105 |
-
"Social": {
|
| 1106 |
-
"Average Score": 0.45872939,
|
| 1107 |
-
"Standard Deviation": 0.05347039576,
|
| 1108 |
-
"Rank": 20
|
| 1109 |
-
},
|
| 1110 |
-
"Chemistry": {
|
| 1111 |
-
"Average Score": 63.65476403379996,
|
| 1112 |
-
"Standard Deviation": null,
|
| 1113 |
-
"Rank": 17
|
| 1114 |
-
},
|
| 1115 |
-
"CPP": {
|
| 1116 |
-
"Average Score": 65.32140697218945,
|
| 1117 |
-
"Standard Deviation": null,
|
| 1118 |
-
"Rank": 13
|
| 1119 |
-
}
|
| 1120 |
-
}
|
| 1121 |
-
},
|
| 1122 |
-
{
|
| 1123 |
-
"config": {
|
| 1124 |
-
"model_name": "claude-3-sonnet",
|
| 1125 |
-
"organization": "Anthropic",
|
| 1126 |
-
"license": "Proprietary",
|
| 1127 |
-
"knowledge_cutoff": "2023/08"
|
| 1128 |
-
},
|
| 1129 |
-
"results": {
|
| 1130 |
-
"OVERALL": {
|
| 1131 |
-
"Average Score": 52.19088595402735,
|
| 1132 |
-
"Standard Deviation": 3.743258734262917,
|
| 1133 |
-
"Rank": 20
|
| 1134 |
-
},
|
| 1135 |
-
"Geometry": {
|
| 1136 |
-
"Average Score": 0.675613638,
|
| 1137 |
-
"Standard Deviation": 0.05275594408,
|
| 1138 |
-
"Rank": 13
|
| 1139 |
-
},
|
| 1140 |
-
"Algebra": {
|
| 1141 |
-
"Average Score": 0.552025728,
|
| 1142 |
-
"Standard Deviation": 0.04122192409,
|
| 1143 |
-
"Rank": 21
|
| 1144 |
-
},
|
| 1145 |
-
"Probability": {
|
| 1146 |
-
"Average Score": 54.0284459891417,
|
| 1147 |
-
"Standard Deviation": null,
|
| 1148 |
-
"Rank": 24
|
| 1149 |
-
},
|
| 1150 |
-
"Logical": {
|
| 1151 |
-
"Average Score": 58.099761779812475,
|
| 1152 |
-
"Standard Deviation": 7.815595203680491,
|
| 1153 |
-
"Rank": 20
|
| 1154 |
-
},
|
| 1155 |
-
"Social": {
|
| 1156 |
-
"Average Score": 0.570437582,
|
| 1157 |
-
"Standard Deviation": 0.08607040862,
|
| 1158 |
-
"Rank": 14
|
| 1159 |
-
},
|
| 1160 |
-
"Chemistry": {
|
| 1161 |
-
"Average Score": 59.784958090634056,
|
| 1162 |
-
"Standard Deviation": null,
|
| 1163 |
-
"Rank": 19
|
| 1164 |
-
},
|
| 1165 |
-
"CPP": {
|
| 1166 |
-
"Average Score": 61.33538592327427,
|
| 1167 |
-
"Standard Deviation": null,
|
| 1168 |
-
"Rank": 15
|
| 1169 |
-
}
|
| 1170 |
-
}
|
| 1171 |
-
},
|
| 1172 |
-
{
|
| 1173 |
-
"config": {
|
| 1174 |
-
"model_name": "qwen1.5-14b-chat",
|
| 1175 |
-
"organization": "Alibaba",
|
| 1176 |
-
"license": "Qianwen LICENSE",
|
| 1177 |
-
"knowledge_cutoff": "2024/02"
|
| 1178 |
-
},
|
| 1179 |
-
"results": {
|
| 1180 |
-
"OVERALL": {
|
| 1181 |
-
"Average Score": 31.56999734729493,
|
| 1182 |
-
"Standard Deviation": 5.42704987916441,
|
| 1183 |
-
"Rank": 29
|
| 1184 |
-
},
|
| 1185 |
-
"Geometry": {
|
| 1186 |
-
"Average Score": 0.452504016,
|
| 1187 |
-
"Standard Deviation": 0.04225594393,
|
| 1188 |
-
"Rank": 26
|
| 1189 |
-
},
|
| 1190 |
-
"Algebra": {
|
| 1191 |
-
"Average Score": 0.538655725,
|
| 1192 |
-
"Standard Deviation": 0.03721542594,
|
| 1193 |
-
"Rank": 22
|
| 1194 |
-
},
|
| 1195 |
-
"Probability": {
|
| 1196 |
-
"Average Score": 41.027908758027046,
|
| 1197 |
-
"Standard Deviation": null,
|
| 1198 |
-
"Rank": 35
|
| 1199 |
-
},
|
| 1200 |
-
"Logical": {
|
| 1201 |
-
"Average Score": 31.638560769720616,
|
| 1202 |
-
"Standard Deviation": 3.175225377796435,
|
| 1203 |
-
"Rank": 38
|
| 1204 |
-
},
|
| 1205 |
-
"Social": {
|
| 1206 |
-
"Average Score": 0.287370142,
|
| 1207 |
-
"Standard Deviation": 0.04264085315,
|
| 1208 |
-
"Rank": 30
|
| 1209 |
-
},
|
| 1210 |
-
"Chemistry": {
|
| 1211 |
-
"Average Score": 37.667977565724996,
|
| 1212 |
-
"Standard Deviation": null,
|
| 1213 |
-
"Rank": 35
|
| 1214 |
-
},
|
| 1215 |
-
"CPP": {
|
| 1216 |
-
"Average Score": 38.552779976347026,
|
| 1217 |
-
"Standard Deviation": null,
|
| 1218 |
-
"Rank": 31
|
| 1219 |
-
}
|
| 1220 |
-
}
|
| 1221 |
-
},
|
| 1222 |
-
{
|
| 1223 |
-
"config": {
|
| 1224 |
-
"model_name": "claude-3-haiku",
|
| 1225 |
-
"organization": "Anthropic",
|
| 1226 |
-
"license": "Proprietary",
|
| 1227 |
-
"knowledge_cutoff": "2023/08"
|
| 1228 |
-
},
|
| 1229 |
-
"results": {
|
| 1230 |
-
"OVERALL": {
|
| 1231 |
-
"Average Score": 42.975259650014074,
|
| 1232 |
-
"Standard Deviation": 2.248602505751528,
|
| 1233 |
-
"Rank": 25
|
| 1234 |
-
},
|
| 1235 |
-
"Geometry": {
|
| 1236 |
-
"Average Score": 0.607993912,
|
| 1237 |
-
"Standard Deviation": 0.05793460748,
|
| 1238 |
-
"Rank": 15
|
| 1239 |
-
},
|
| 1240 |
-
"Algebra": {
|
| 1241 |
-
"Average Score": 0.520054055,
|
| 1242 |
-
"Standard Deviation": 0.03333544511,
|
| 1243 |
-
"Rank": 23
|
| 1244 |
-
},
|
| 1245 |
-
"Probability": {
|
| 1246 |
-
"Average Score": 52.44184603289214,
|
| 1247 |
-
"Standard Deviation": null,
|
| 1248 |
-
"Rank": 28
|
| 1249 |
-
},
|
| 1250 |
-
"Logical": {
|
| 1251 |
-
"Average Score": 50.38523351226464,
|
| 1252 |
-
"Standard Deviation": 1.9928131873345676,
|
| 1253 |
-
"Rank": 24
|
| 1254 |
-
},
|
| 1255 |
-
"Social": {
|
| 1256 |
-
"Average Score": 0.551083976,
|
| 1257 |
-
"Standard Deviation": 0.05374722539,
|
| 1258 |
-
"Rank": 16
|
| 1259 |
-
},
|
| 1260 |
-
"Chemistry": {
|
| 1261 |
-
"Average Score": 54.99584531372778,
|
| 1262 |
-
"Standard Deviation": null,
|
| 1263 |
-
"Rank": 20
|
| 1264 |
-
},
|
| 1265 |
-
"CPP": {
|
| 1266 |
-
"Average Score": 56.40200048817984,
|
| 1267 |
-
"Standard Deviation": null,
|
| 1268 |
-
"Rank": 16
|
| 1269 |
-
}
|
| 1270 |
-
}
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"config": {
|
| 1274 |
-
"model_name": "claude-2.1",
|
| 1275 |
-
"organization": "Anthropic",
|
| 1276 |
-
"license": "Proprietary",
|
| 1277 |
-
"knowledge_cutoff": "Unknown"
|
| 1278 |
-
},
|
| 1279 |
-
"results": {
|
| 1280 |
-
"OVERALL": {
|
| 1281 |
-
"Average Score": 23.82704986290717,
|
| 1282 |
-
"Standard Deviation": 1.6337262681919007,
|
| 1283 |
-
"Rank": 37
|
| 1284 |
-
},
|
| 1285 |
-
"Geometry": {
|
| 1286 |
-
"Average Score": 0.62752395,
|
| 1287 |
-
"Standard Deviation": 0.07232659398,
|
| 1288 |
-
"Rank": 14
|
| 1289 |
-
},
|
| 1290 |
-
"Algebra": {
|
| 1291 |
-
"Average Score": 0.508849609,
|
| 1292 |
-
"Standard Deviation": 0.0346897465,
|
| 1293 |
-
"Rank": 24
|
| 1294 |
-
},
|
| 1295 |
-
"Probability": {
|
| 1296 |
-
"Average Score": 42.82280874207299,
|
| 1297 |
-
"Standard Deviation": null,
|
| 1298 |
-
"Rank": 32
|
| 1299 |
-
},
|
| 1300 |
-
"Logical": {
|
| 1301 |
-
"Average Score": 47.40647506260718,
|
| 1302 |
-
"Standard Deviation": 3.5140099122016686,
|
| 1303 |
-
"Rank": 25
|
| 1304 |
-
},
|
| 1305 |
-
"Social": {
|
| 1306 |
-
"Average Score": 0.333804568,
|
| 1307 |
-
"Standard Deviation": 0.03775548253,
|
| 1308 |
-
"Rank": 27
|
| 1309 |
-
},
|
| 1310 |
-
"Chemistry": {
|
| 1311 |
-
"Average Score": 46.09889239661357,
|
| 1312 |
-
"Standard Deviation": null,
|
| 1313 |
-
"Rank": 25
|
| 1314 |
-
},
|
| 1315 |
-
"CPP": {
|
| 1316 |
-
"Average Score": 47.23672563994903,
|
| 1317 |
-
"Standard Deviation": null,
|
| 1318 |
-
"Rank": 21
|
| 1319 |
-
}
|
| 1320 |
-
}
|
| 1321 |
-
},
|
| 1322 |
-
{
|
| 1323 |
-
"config": {
|
| 1324 |
-
"model_name": "mistral-8x7b-instruct-v0.1",
|
| 1325 |
-
"organization": "Mistral",
|
| 1326 |
-
"license": "Apache 2.0",
|
| 1327 |
-
"knowledge_cutoff": "2023/12"
|
| 1328 |
-
},
|
| 1329 |
-
"results": {
|
| 1330 |
-
"OVERALL": {
|
| 1331 |
-
"Average Score": 26.279729527476174,
|
| 1332 |
-
"Standard Deviation": 1.7823676900027476,
|
| 1333 |
-
"Rank": 33
|
| 1334 |
-
},
|
| 1335 |
-
"Geometry": {
|
| 1336 |
-
"Average Score": 0.432216097,
|
| 1337 |
-
"Standard Deviation": 0.04747949254,
|
| 1338 |
-
"Rank": 29
|
| 1339 |
-
},
|
| 1340 |
-
"Algebra": {
|
| 1341 |
-
"Average Score": 0.478314888,
|
| 1342 |
-
"Standard Deviation": 0.01998797419,
|
| 1343 |
-
"Rank": 25
|
| 1344 |
-
},
|
| 1345 |
-
"Probability": {
|
| 1346 |
-
"Average Score": 42.27303178662447,
|
| 1347 |
-
"Standard Deviation": null,
|
| 1348 |
-
"Rank": 33
|
| 1349 |
-
},
|
| 1350 |
-
"Logical": {
|
| 1351 |
-
"Average Score": 34.58281320758576,
|
| 1352 |
-
"Standard Deviation": 2.5548927504271073,
|
| 1353 |
-
"Rank": 33
|
| 1354 |
-
},
|
| 1355 |
-
"Social": {
|
| 1356 |
-
"Average Score": 0.251949622,
|
| 1357 |
-
"Standard Deviation": 0.03346674405,
|
| 1358 |
-
"Rank": 35
|
| 1359 |
-
},
|
| 1360 |
-
"Chemistry": {
|
| 1361 |
-
"Average Score": 43.47423835615602,
|
| 1362 |
-
"Standard Deviation": null,
|
| 1363 |
-
"Rank": 29
|
| 1364 |
-
},
|
| 1365 |
-
"CPP": {
|
| 1366 |
-
"Average Score": 44.533118241976666,
|
| 1367 |
-
"Standard Deviation": null,
|
| 1368 |
-
"Rank": 25
|
| 1369 |
-
}
|
| 1370 |
-
}
|
| 1371 |
-
},
|
| 1372 |
-
{
|
| 1373 |
-
"config": {
|
| 1374 |
-
"model_name": "claude-2.0",
|
| 1375 |
-
"organization": "Anthropic",
|
| 1376 |
-
"license": "Proprietary",
|
| 1377 |
-
"knowledge_cutoff": "Unknown"
|
| 1378 |
-
},
|
| 1379 |
-
"results": {
|
| 1380 |
-
"OVERALL": {
|
| 1381 |
-
"Average Score": 20.490629074737296,
|
| 1382 |
-
"Standard Deviation": 0.4821482730133453,
|
| 1383 |
-
"Rank": 40
|
| 1384 |
-
},
|
| 1385 |
-
"Geometry": {
|
| 1386 |
-
"Average Score": 0.604141967,
|
| 1387 |
-
"Standard Deviation": 0.05116441826,
|
| 1388 |
-
"Rank": 16
|
| 1389 |
-
},
|
| 1390 |
-
"Algebra": {
|
| 1391 |
-
"Average Score": 0.474350734,
|
| 1392 |
-
"Standard Deviation": 0.01510393066,
|
| 1393 |
-
"Rank": 26
|
| 1394 |
-
},
|
| 1395 |
-
"Probability": {
|
| 1396 |
-
"Average Score": 45.15580067803421,
|
| 1397 |
-
"Standard Deviation": null,
|
| 1398 |
-
"Rank": 31
|
| 1399 |
-
},
|
| 1400 |
-
"Logical": {
|
| 1401 |
-
"Average Score": 43.65660021552717,
|
| 1402 |
-
"Standard Deviation": 4.959029305063026,
|
| 1403 |
-
"Rank": 27
|
| 1404 |
-
},
|
| 1405 |
-
"Social": {
|
| 1406 |
-
"Average Score": 0.469422836,
|
| 1407 |
-
"Standard Deviation": 0.05999901796,
|
| 1408 |
-
"Rank": 19
|
| 1409 |
-
},
|
| 1410 |
-
"Chemistry": {
|
| 1411 |
-
"Average Score": 49.53201090067431,
|
| 1412 |
-
"Standard Deviation": null,
|
| 1413 |
-
"Rank": 23
|
| 1414 |
-
},
|
| 1415 |
-
"CPP": {
|
| 1416 |
-
"Average Score": 50.773143448036464,
|
| 1417 |
-
"Standard Deviation": null,
|
| 1418 |
-
"Rank": 19
|
| 1419 |
-
}
|
| 1420 |
-
}
|
| 1421 |
-
},
|
| 1422 |
-
{
|
| 1423 |
-
"config": {
|
| 1424 |
-
"model_name": "starling-lm-7b-beta",
|
| 1425 |
-
"organization": "Nexusflow",
|
| 1426 |
-
"license": "Apache-2.0",
|
| 1427 |
-
"knowledge_cutoff": "2024/03"
|
| 1428 |
-
},
|
| 1429 |
-
"results": {
|
| 1430 |
-
"OVERALL": {
|
| 1431 |
-
"Average Score": 43.0415265396966,
|
| 1432 |
-
"Standard Deviation": 0.8770524316858576,
|
| 1433 |
-
"Rank": 24
|
| 1434 |
-
},
|
| 1435 |
-
"Geometry": {
|
| 1436 |
-
"Average Score": 0.446654388,
|
| 1437 |
-
"Standard Deviation": 0.05637864999,
|
| 1438 |
-
"Rank": 28
|
| 1439 |
-
},
|
| 1440 |
-
"Algebra": {
|
| 1441 |
-
"Average Score": 0.473952749,
|
| 1442 |
-
"Standard Deviation": 0.01584301288,
|
| 1443 |
-
"Rank": 27
|
| 1444 |
-
},
|
| 1445 |
-
"Probability": {
|
| 1446 |
-
"Average Score": 41.320066911500234,
|
| 1447 |
-
"Standard Deviation": null,
|
| 1448 |
-
"Rank": 34
|
| 1449 |
-
},
|
| 1450 |
-
"Logical": {
|
| 1451 |
-
"Average Score": 39.79665241383638,
|
| 1452 |
-
"Standard Deviation": 3.4711628274016544,
|
| 1453 |
-
"Rank": 30
|
| 1454 |
-
},
|
| 1455 |
-
"Social": {
|
| 1456 |
-
"Average Score": 0.380021662,
|
| 1457 |
-
"Standard Deviation": 0.04622452748,
|
| 1458 |
-
"Rank": 25
|
| 1459 |
-
},
|
| 1460 |
-
"Chemistry": {
|
| 1461 |
-
"Average Score": 37.39896886078588,
|
| 1462 |
-
"Standard Deviation": null,
|
| 1463 |
-
"Rank": 36
|
| 1464 |
-
},
|
| 1465 |
-
"CPP": {
|
| 1466 |
-
"Average Score": 38.27587102395908,
|
| 1467 |
-
"Standard Deviation": null,
|
| 1468 |
-
"Rank": 32
|
| 1469 |
-
}
|
| 1470 |
-
}
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"config": {
|
| 1474 |
-
"model_name": "gemini-1.0-pro-001",
|
| 1475 |
-
"organization": "Google",
|
| 1476 |
-
"license": "Proprietary",
|
| 1477 |
-
"knowledge_cutoff": "2023/04"
|
| 1478 |
-
},
|
| 1479 |
-
"results": {
|
| 1480 |
-
"OVERALL": {
|
| 1481 |
-
"Average Score": 45.78126809517331,
|
| 1482 |
-
"Standard Deviation": 3.7275133674569783,
|
| 1483 |
-
"Rank": 23
|
| 1484 |
-
},
|
| 1485 |
-
"Geometry": {
|
| 1486 |
-
"Average Score": 0.578347959,
|
| 1487 |
-
"Standard Deviation": 0.04242873607,
|
| 1488 |
-
"Rank": 19
|
| 1489 |
-
},
|
| 1490 |
-
"Algebra": {
|
| 1491 |
-
"Average Score": 0.462417786,
|
| 1492 |
-
"Standard Deviation": 0.01668313635,
|
| 1493 |
-
"Rank": 28
|
| 1494 |
-
},
|
| 1495 |
-
"Probability": {
|
| 1496 |
-
"Average Score": 31.410607001114293,
|
| 1497 |
-
"Standard Deviation": null,
|
| 1498 |
-
"Rank": 42
|
| 1499 |
-
},
|
| 1500 |
-
"Logical": {
|
| 1501 |
-
"Average Score": 21.717362428653246,
|
| 1502 |
-
"Standard Deviation": 4.392290522642325,
|
| 1503 |
-
"Rank": 44
|
| 1504 |
-
},
|
| 1505 |
-
"Social": {
|
| 1506 |
-
"Average Score": 0.130790863,
|
| 1507 |
-
"Standard Deviation": 0.02800188173,
|
| 1508 |
-
"Rank": 45
|
| 1509 |
-
},
|
| 1510 |
-
"Chemistry": {
|
| 1511 |
-
"Average Score": 44.14314678087462,
|
| 1512 |
-
"Standard Deviation": null,
|
| 1513 |
-
"Rank": 27
|
| 1514 |
-
},
|
| 1515 |
-
"CPP": {
|
| 1516 |
-
"Average Score": 45.22204471452975,
|
| 1517 |
-
"Standard Deviation": null,
|
| 1518 |
-
"Rank": 23
|
| 1519 |
-
}
|
| 1520 |
-
}
|
| 1521 |
-
},
|
| 1522 |
-
{
|
| 1523 |
-
"config": {
|
| 1524 |
-
"model_name": "openchat-3.5-0106",
|
| 1525 |
-
"organization": "OpenChat",
|
| 1526 |
-
"license": "Apache-2.0",
|
| 1527 |
-
"knowledge_cutoff": "2024/01"
|
| 1528 |
-
},
|
| 1529 |
-
"results": {
|
| 1530 |
-
"OVERALL": {
|
| 1531 |
-
"Average Score": 23.85666609339201,
|
| 1532 |
-
"Standard Deviation": 1.341285455536348,
|
| 1533 |
-
"Rank": 36
|
| 1534 |
-
},
|
| 1535 |
-
"Geometry": {
|
| 1536 |
-
"Average Score": 0.38715246,
|
| 1537 |
-
"Standard Deviation": 0.03701851946,
|
| 1538 |
-
"Rank": 32
|
| 1539 |
-
},
|
| 1540 |
-
"Algebra": {
|
| 1541 |
-
"Average Score": 0.441233712,
|
| 1542 |
-
"Standard Deviation": 0.01135753754,
|
| 1543 |
-
"Rank": 29
|
| 1544 |
-
},
|
| 1545 |
-
"Probability": {
|
| 1546 |
-
"Average Score": 40.37790468557232,
|
| 1547 |
-
"Standard Deviation": null,
|
| 1548 |
-
"Rank": 36
|
| 1549 |
-
},
|
| 1550 |
-
"Logical": {
|
| 1551 |
-
"Average Score": 35.1573373260624,
|
| 1552 |
-
"Standard Deviation": 2.485128777146724,
|
| 1553 |
-
"Rank": 32
|
| 1554 |
-
},
|
| 1555 |
-
"Social": {
|
| 1556 |
-
"Average Score": 0.250891608,
|
| 1557 |
-
"Standard Deviation": 0.03253769914,
|
| 1558 |
-
"Rank": 36
|
| 1559 |
-
},
|
| 1560 |
-
"Chemistry": {
|
| 1561 |
-
"Average Score": 32.96322247853182,
|
| 1562 |
-
"Standard Deviation": null,
|
| 1563 |
-
"Rank": 37
|
| 1564 |
-
},
|
| 1565 |
-
"CPP": {
|
| 1566 |
-
"Average Score": 33.70639271807677,
|
| 1567 |
-
"Standard Deviation": null,
|
| 1568 |
-
"Rank": 33
|
| 1569 |
-
}
|
| 1570 |
-
}
|
| 1571 |
-
},
|
| 1572 |
-
{
|
| 1573 |
-
"config": {
|
| 1574 |
-
"model_name": "openchat-3.5",
|
| 1575 |
-
"organization": "OpenChat",
|
| 1576 |
-
"license": "Apache-2.0",
|
| 1577 |
-
"knowledge_cutoff": "2023/11"
|
| 1578 |
-
},
|
| 1579 |
-
"results": {
|
| 1580 |
-
"OVERALL": {
|
| 1581 |
-
"Average Score": 23.63538251797928,
|
| 1582 |
-
"Standard Deviation": 2.0516295921862095,
|
| 1583 |
-
"Rank": 38
|
| 1584 |
-
},
|
| 1585 |
-
"Geometry": {
|
| 1586 |
-
"Average Score": 0.401699069,
|
| 1587 |
-
"Standard Deviation": 0.03410726557,
|
| 1588 |
-
"Rank": 30
|
| 1589 |
-
},
|
| 1590 |
-
"Algebra": {
|
| 1591 |
-
"Average Score": 0.414095336,
|
| 1592 |
-
"Standard Deviation": 0.01881964261,
|
| 1593 |
-
"Rank": 31
|
| 1594 |
-
},
|
| 1595 |
-
"Probability": {
|
| 1596 |
-
"Average Score": 36.00454588244476,
|
| 1597 |
-
"Standard Deviation": null,
|
| 1598 |
-
"Rank": 38
|
| 1599 |
-
},
|
| 1600 |
-
"Logical": {
|
| 1601 |
-
"Average Score": 34.029859502735654,
|
| 1602 |
-
"Standard Deviation": 3.354098427500673,
|
| 1603 |
-
"Rank": 35
|
| 1604 |
-
},
|
| 1605 |
-
"Social": {
|
| 1606 |
-
"Average Score": 0.319991655,
|
| 1607 |
-
"Standard Deviation": 0.04502478724,
|
| 1608 |
-
"Rank": 29
|
| 1609 |
-
},
|
| 1610 |
-
"Chemistry": {
|
| 1611 |
-
"Average Score": 32.29778226319944,
|
| 1612 |
-
"Standard Deviation": null,
|
| 1613 |
-
"Rank": 38
|
| 1614 |
-
},
|
| 1615 |
-
"CPP": {
|
| 1616 |
-
"Average Score": 33.020911255646965,
|
| 1617 |
-
"Standard Deviation": null,
|
| 1618 |
-
"Rank": 34
|
| 1619 |
-
}
|
| 1620 |
-
}
|
| 1621 |
-
},
|
| 1622 |
-
{
|
| 1623 |
-
"config": {
|
| 1624 |
-
"model_name": "command-r-(08-2024)",
|
| 1625 |
-
"organization": "Cohere",
|
| 1626 |
-
"license": "CC-BY-NC-4.0",
|
| 1627 |
-
"knowledge_cutoff": "2024/08"
|
| 1628 |
-
},
|
| 1629 |
-
"results": {
|
| 1630 |
-
"OVERALL": {
|
| 1631 |
-
"Average Score": 38.783798277856995,
|
| 1632 |
-
"Standard Deviation": 1.1948096596199191,
|
| 1633 |
-
"Rank": 27
|
| 1634 |
-
},
|
| 1635 |
-
"Geometry": {
|
| 1636 |
-
"Average Score": 0.448300727,
|
| 1637 |
-
"Standard Deviation": 0.04996362328,
|
| 1638 |
-
"Rank": 27
|
| 1639 |
-
},
|
| 1640 |
-
"Algebra": {
|
| 1641 |
-
"Average Score": 0.417519167,
|
| 1642 |
-
"Standard Deviation": 0.01822196902,
|
| 1643 |
-
"Rank": 30
|
| 1644 |
-
},
|
| 1645 |
-
"Probability": {
|
| 1646 |
-
"Average Score": 38.019523941917335,
|
| 1647 |
-
"Standard Deviation": null,
|
| 1648 |
-
"Rank": 37
|
| 1649 |
-
},
|
| 1650 |
-
"Logical": {
|
| 1651 |
-
"Average Score": 23.408826179018206,
|
| 1652 |
-
"Standard Deviation": 0.9355701468205376,
|
| 1653 |
-
"Rank": 42
|
| 1654 |
-
},
|
| 1655 |
-
"Social": {
|
| 1656 |
-
"Average Score": 0.276088379,
|
| 1657 |
-
"Standard Deviation": 0.03295234688,
|
| 1658 |
-
"Rank": 32
|
| 1659 |
-
},
|
| 1660 |
-
"Chemistry": {
|
| 1661 |
-
"Average Score": 38.699171059988636,
|
| 1662 |
-
"Standard Deviation": null,
|
| 1663 |
-
"Rank": 34
|
| 1664 |
-
},
|
| 1665 |
-
"CPP": {
|
| 1666 |
-
"Average Score": 39.61492485677676,
|
| 1667 |
-
"Standard Deviation": null,
|
| 1668 |
-
"Rank": 30
|
| 1669 |
-
}
|
| 1670 |
-
}
|
| 1671 |
-
},
|
| 1672 |
-
{
|
| 1673 |
-
"config": {
|
| 1674 |
-
"model_name": "gemma-1.1-7b-it",
|
| 1675 |
-
"organization": "Google",
|
| 1676 |
-
"license": "Gemma License",
|
| 1677 |
-
"knowledge_cutoff": "2024/02"
|
| 1678 |
-
},
|
| 1679 |
-
"results": {
|
| 1680 |
-
"OVERALL": {
|
| 1681 |
-
"Average Score": 20.965269549151657,
|
| 1682 |
-
"Standard Deviation": 0.6031600560715249,
|
| 1683 |
-
"Rank": 39
|
| 1684 |
-
},
|
| 1685 |
-
"Geometry": {
|
| 1686 |
-
"Average Score": 0.324170977,
|
| 1687 |
-
"Standard Deviation": 0.04668553765,
|
| 1688 |
-
"Rank": 35
|
| 1689 |
-
},
|
| 1690 |
-
"Algebra": {
|
| 1691 |
-
"Average Score": 0.398684697,
|
| 1692 |
-
"Standard Deviation": 0.01982398259,
|
| 1693 |
-
"Rank": 32
|
| 1694 |
-
},
|
| 1695 |
-
"Probability": {
|
| 1696 |
-
"Average Score": 30.98345832281905,
|
| 1697 |
-
"Standard Deviation": null,
|
| 1698 |
-
"Rank": 43
|
| 1699 |
-
},
|
| 1700 |
-
"Logical": {
|
| 1701 |
-
"Average Score": 33.36570116785516,
|
| 1702 |
-
"Standard Deviation": 3.8824795120929765,
|
| 1703 |
-
"Rank": 36
|
| 1704 |
-
},
|
| 1705 |
-
"Social": {
|
| 1706 |
-
"Average Score": 0.179073276,
|
| 1707 |
-
"Standard Deviation": 0.02009658805,
|
| 1708 |
-
"Rank": 41
|
| 1709 |
-
},
|
| 1710 |
-
"Chemistry": {
|
| 1711 |
-
"Average Score": 41.66173653808921,
|
| 1712 |
-
"Standard Deviation": null,
|
| 1713 |
-
"Rank": 31
|
| 1714 |
-
},
|
| 1715 |
-
"CPP": {
|
| 1716 |
-
"Average Score": 42.666504105798204,
|
| 1717 |
-
"Standard Deviation": null,
|
| 1718 |
-
"Rank": 27
|
| 1719 |
-
}
|
| 1720 |
-
}
|
| 1721 |
-
},
|
| 1722 |
-
{
|
| 1723 |
-
"config": {
|
| 1724 |
-
"model_name": "llama3-8b-instruct",
|
| 1725 |
-
"organization": "Meta",
|
| 1726 |
-
"license": "Llama 3 Community",
|
| 1727 |
-
"knowledge_cutoff": "2023/03"
|
| 1728 |
-
},
|
| 1729 |
-
"results": {
|
| 1730 |
-
"OVERALL": {
|
| 1731 |
-
"Average Score": 30.183633696164936,
|
| 1732 |
-
"Standard Deviation": 3.5901082045571266,
|
| 1733 |
-
"Rank": 31
|
| 1734 |
-
},
|
| 1735 |
-
"Geometry": {
|
| 1736 |
-
"Average Score": 0.367143758,
|
| 1737 |
-
"Standard Deviation": 0.04363680358,
|
| 1738 |
-
"Rank": 33
|
| 1739 |
-
},
|
| 1740 |
-
"Algebra": {
|
| 1741 |
-
"Average Score": 0.391480973,
|
| 1742 |
-
"Standard Deviation": 0.02757445266,
|
| 1743 |
-
"Rank": 33
|
| 1744 |
-
},
|
| 1745 |
-
"Probability": {
|
| 1746 |
-
"Average Score": 34.51621975866105,
|
| 1747 |
-
"Standard Deviation": null,
|
| 1748 |
-
"Rank": 39
|
| 1749 |
-
},
|
| 1750 |
-
"Logical": {
|
| 1751 |
-
"Average Score": 45.27560737491475,
|
| 1752 |
-
"Standard Deviation": 4.639305724878496,
|
| 1753 |
-
"Rank": 26
|
| 1754 |
-
},
|
| 1755 |
-
"Social": {
|
| 1756 |
-
"Average Score": 0.336373622,
|
| 1757 |
-
"Standard Deviation": 0.05762408512,
|
| 1758 |
-
"Rank": 26
|
| 1759 |
-
},
|
| 1760 |
-
"Chemistry": {
|
| 1761 |
-
"Average Score": 44.271144265487514,
|
| 1762 |
-
"Standard Deviation": null,
|
| 1763 |
-
"Rank": 26
|
| 1764 |
-
},
|
| 1765 |
-
"CPP": {
|
| 1766 |
-
"Average Score": 45.35392139264795,
|
| 1767 |
-
"Standard Deviation": null,
|
| 1768 |
-
"Rank": 22
|
| 1769 |
-
}
|
| 1770 |
-
}
|
| 1771 |
-
},
|
| 1772 |
-
{
|
| 1773 |
-
"config": {
|
| 1774 |
-
"model_name": "gemma-2-2b-it",
|
| 1775 |
-
"organization": "Google",
|
| 1776 |
-
"license": "Gemma License",
|
| 1777 |
-
"knowledge_cutoff": "2024/07"
|
| 1778 |
-
},
|
| 1779 |
-
"results": {
|
| 1780 |
-
"OVERALL": {
|
| 1781 |
-
"Average Score": 47.37377937645159,
|
| 1782 |
-
"Standard Deviation": 2.72420190928707,
|
| 1783 |
-
"Rank": 22
|
| 1784 |
-
},
|
| 1785 |
-
"Geometry": {
|
| 1786 |
-
"Average Score": 0.395006676,
|
| 1787 |
-
"Standard Deviation": 0.05882607713,
|
| 1788 |
-
"Rank": 31
|
| 1789 |
-
},
|
| 1790 |
-
"Algebra": {
|
| 1791 |
-
"Average Score": 0.379391887,
|
| 1792 |
-
"Standard Deviation": 0.01722410785,
|
| 1793 |
-
"Rank": 34
|
| 1794 |
-
},
|
| 1795 |
-
"Probability": {
|
| 1796 |
-
"Average Score": 33.90530403382374,
|
| 1797 |
-
"Standard Deviation": null,
|
| 1798 |
-
"Rank": 41
|
| 1799 |
-
},
|
| 1800 |
-
"Logical": {
|
| 1801 |
-
"Average Score": 37.64262561604027,
|
| 1802 |
-
"Standard Deviation": 3.0627256408495804,
|
| 1803 |
-
"Rank": 31
|
| 1804 |
-
},
|
| 1805 |
-
"Social": {
|
| 1806 |
-
"Average Score": 0.393482094,
|
| 1807 |
-
"Standard Deviation": 0.06450214024,
|
| 1808 |
-
"Rank": 23
|
| 1809 |
-
},
|
| 1810 |
-
"Chemistry": {
|
| 1811 |
-
"Average Score": 29.883648650177584,
|
| 1812 |
-
"Standard Deviation": null,
|
| 1813 |
-
"Rank": 40
|
| 1814 |
-
},
|
| 1815 |
-
"CPP": {
|
| 1816 |
-
"Average Score": 30.53406933106768,
|
| 1817 |
-
"Standard Deviation": null,
|
| 1818 |
-
"Rank": 36
|
| 1819 |
-
}
|
| 1820 |
-
}
|
| 1821 |
-
},
|
| 1822 |
-
{
|
| 1823 |
-
"config": {
|
| 1824 |
-
"model_name": "starling-lm-7b-alpha",
|
| 1825 |
-
"organization": "Nexusflow",
|
| 1826 |
-
"license": "Apache-2.0",
|
| 1827 |
-
"knowledge_cutoff": "2023/11"
|
| 1828 |
-
},
|
| 1829 |
-
"results": {
|
| 1830 |
-
"OVERALL": {
|
| 1831 |
-
"Average Score": 24.34505731078066,
|
| 1832 |
-
"Standard Deviation": 1.4660872513914562,
|
| 1833 |
-
"Rank": 35
|
| 1834 |
-
},
|
| 1835 |
-
"Geometry": {
|
| 1836 |
-
"Average Score": 0.336782578,
|
| 1837 |
-
"Standard Deviation": 0.04069449132,
|
| 1838 |
-
"Rank": 34
|
| 1839 |
-
},
|
| 1840 |
-
"Algebra": {
|
| 1841 |
-
"Average Score": 0.371551932,
|
| 1842 |
-
"Standard Deviation": 0.03367241745,
|
| 1843 |
-
"Rank": 35
|
| 1844 |
-
},
|
| 1845 |
-
"Probability": {
|
| 1846 |
-
"Average Score": 34.51613212227484,
|
| 1847 |
-
"Standard Deviation": null,
|
| 1848 |
-
"Rank": 40
|
| 1849 |
-
},
|
| 1850 |
-
"Logical": {
|
| 1851 |
-
"Average Score": 29.88612695085449,
|
| 1852 |
-
"Standard Deviation": 2.4070524024678672,
|
| 1853 |
-
"Rank": 40
|
| 1854 |
-
},
|
| 1855 |
-
"Social": {
|
| 1856 |
-
"Average Score": 0.271975534,
|
| 1857 |
-
"Standard Deviation": 0.04266753408,
|
| 1858 |
-
"Rank": 33
|
| 1859 |
-
},
|
| 1860 |
-
"Chemistry": {
|
| 1861 |
-
"Average Score": 29.442057363491365,
|
| 1862 |
-
"Standard Deviation": null,
|
| 1863 |
-
"Rank": 41
|
| 1864 |
-
},
|
| 1865 |
-
"CPP": {
|
| 1866 |
-
"Average Score": 30.07926487356878,
|
| 1867 |
-
"Standard Deviation": null,
|
| 1868 |
-
"Rank": 37
|
| 1869 |
-
}
|
| 1870 |
-
}
|
| 1871 |
-
},
|
| 1872 |
-
{
|
| 1873 |
-
"config": {
|
| 1874 |
-
"model_name": "qwen1.5-4b-chat",
|
| 1875 |
-
"organization": "Alibaba",
|
| 1876 |
-
"license": "Qianwen LICENSE",
|
| 1877 |
-
"knowledge_cutoff": "2024/02"
|
| 1878 |
-
},
|
| 1879 |
-
"results": {
|
| 1880 |
-
"OVERALL": {
|
| 1881 |
-
"Average Score": 7.19753150259024,
|
| 1882 |
-
"Standard Deviation": 0.6175113365944395,
|
| 1883 |
-
"Rank": 52
|
| 1884 |
-
},
|
| 1885 |
-
"Geometry": {
|
| 1886 |
-
"Average Score": 0.215834522,
|
| 1887 |
-
"Standard Deviation": 0.0363766363,
|
| 1888 |
-
"Rank": 39
|
| 1889 |
-
},
|
| 1890 |
-
"Algebra": {
|
| 1891 |
-
"Average Score": 0.305589811,
|
| 1892 |
-
"Standard Deviation": 0.02354198912,
|
| 1893 |
-
"Rank": 36
|
| 1894 |
-
},
|
| 1895 |
-
"Probability": {
|
| 1896 |
-
"Average Score": 15.124506890648007,
|
| 1897 |
-
"Standard Deviation": null,
|
| 1898 |
-
"Rank": 49
|
| 1899 |
-
},
|
| 1900 |
-
"Logical": {
|
| 1901 |
-
"Average Score": 11.67206257803879,
|
| 1902 |
-
"Standard Deviation": 1.140401009846497,
|
| 1903 |
-
"Rank": 51
|
| 1904 |
-
},
|
| 1905 |
-
"Social": {
|
| 1906 |
-
"Average Score": 0.18195615,
|
| 1907 |
-
"Standard Deviation": 0.02269805277,
|
| 1908 |
-
"Rank": 40
|
| 1909 |
-
},
|
| 1910 |
-
"Chemistry": {
|
| 1911 |
-
"Average Score": 12.825435835657133,
|
| 1912 |
-
"Standard Deviation": null,
|
| 1913 |
-
"Rank": 52
|
| 1914 |
-
},
|
| 1915 |
-
"CPP": {
|
| 1916 |
-
"Average Score": 13.21208067122554,
|
| 1917 |
-
"Standard Deviation": null,
|
| 1918 |
-
"Rank": 47
|
| 1919 |
-
}
|
| 1920 |
-
}
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"config": {
|
| 1924 |
-
"model_name": "command-r-(04-2024)",
|
| 1925 |
-
"organization": "Cohere",
|
| 1926 |
-
"license": "CC-BY-NC-4.0",
|
| 1927 |
-
"knowledge_cutoff": "2024/04"
|
| 1928 |
-
},
|
| 1929 |
-
"results": {
|
| 1930 |
-
"OVERALL": {
|
| 1931 |
-
"Average Score": 26.20787727166716,
|
| 1932 |
-
"Standard Deviation": 1.6793980036057201,
|
| 1933 |
-
"Rank": 34
|
| 1934 |
-
},
|
| 1935 |
-
"Geometry": {
|
| 1936 |
-
"Average Score": 0.300416698,
|
| 1937 |
-
"Standard Deviation": 0.03485612736,
|
| 1938 |
-
"Rank": 36
|
| 1939 |
-
},
|
| 1940 |
-
"Algebra": {
|
| 1941 |
-
"Average Score": 0.293120231,
|
| 1942 |
-
"Standard Deviation": 0.032926484,
|
| 1943 |
-
"Rank": 37
|
| 1944 |
-
},
|
| 1945 |
-
"Probability": {
|
| 1946 |
-
"Average Score": 28.551833516483626,
|
| 1947 |
-
"Standard Deviation": null,
|
| 1948 |
-
"Rank": 44
|
| 1949 |
-
},
|
| 1950 |
-
"Logical": {
|
| 1951 |
-
"Average Score": 30.83782425033377,
|
| 1952 |
-
"Standard Deviation": 3.4266833154577383,
|
| 1953 |
-
"Rank": 39
|
| 1954 |
-
},
|
| 1955 |
-
"Social": {
|
| 1956 |
-
"Average Score": 0.283882949,
|
| 1957 |
-
"Standard Deviation": 0.03336901148,
|
| 1958 |
-
"Rank": 31
|
| 1959 |
-
},
|
| 1960 |
-
"Chemistry": {
|
| 1961 |
-
"Average Score": 40.38004181614496,
|
| 1962 |
-
"Standard Deviation": null,
|
| 1963 |
-
"Rank": 32
|
| 1964 |
-
},
|
| 1965 |
-
"CPP": {
|
| 1966 |
-
"Average Score": 41.346336503003236,
|
| 1967 |
-
"Standard Deviation": null,
|
| 1968 |
-
"Rank": 28
|
| 1969 |
-
}
|
| 1970 |
-
}
|
| 1971 |
-
},
|
| 1972 |
-
{
|
| 1973 |
-
"config": {
|
| 1974 |
-
"model_name": "vicuna-33b",
|
| 1975 |
-
"organization": "LMSYS",
|
| 1976 |
-
"license": "Non-commercial",
|
| 1977 |
-
"knowledge_cutoff": "2023/08"
|
| 1978 |
-
},
|
| 1979 |
-
"results": {
|
| 1980 |
-
"OVERALL": {
|
| 1981 |
-
"Average Score": 19.726298678709266,
|
| 1982 |
-
"Standard Deviation": 1.0771354692793496,
|
| 1983 |
-
"Rank": 41
|
| 1984 |
-
},
|
| 1985 |
-
"Geometry": {
|
| 1986 |
-
"Average Score": 0.208284679,
|
| 1987 |
-
"Standard Deviation": 0.03937771461,
|
| 1988 |
-
"Rank": 40
|
| 1989 |
-
},
|
| 1990 |
-
"Algebra": {
|
| 1991 |
-
"Average Score": 0.248994048,
|
| 1992 |
-
"Standard Deviation": 0.02668175054,
|
| 1993 |
-
"Rank": 39
|
| 1994 |
-
},
|
| 1995 |
-
"Probability": {
|
| 1996 |
-
"Average Score": 23.2308538772627,
|
| 1997 |
-
"Standard Deviation": null,
|
| 1998 |
-
"Rank": 47
|
| 1999 |
-
},
|
| 2000 |
-
"Logical": {
|
| 2001 |
-
"Average Score": 19.488409585540122,
|
| 2002 |
-
"Standard Deviation": 0.7913465863319494,
|
| 2003 |
-
"Rank": 46
|
| 2004 |
-
},
|
| 2005 |
-
"Social": {
|
| 2006 |
-
"Average Score": 0.257623798,
|
| 2007 |
-
"Standard Deviation": 0.02653724437,
|
| 2008 |
-
"Rank": 34
|
| 2009 |
-
},
|
| 2010 |
-
"Chemistry": {
|
| 2011 |
-
"Average Score": 27.198874596635843,
|
| 2012 |
-
"Standard Deviation": null,
|
| 2013 |
-
"Rank": 43
|
| 2014 |
-
},
|
| 2015 |
-
"CPP": {
|
| 2016 |
-
"Average Score": 28.01838653090379,
|
| 2017 |
-
"Standard Deviation": null,
|
| 2018 |
-
"Rank": 38
|
| 2019 |
-
}
|
| 2020 |
-
}
|
| 2021 |
-
},
|
| 2022 |
-
{
|
| 2023 |
-
"config": {
|
| 2024 |
-
"model_name": "gemma-7b-it",
|
| 2025 |
-
"organization": "Google",
|
| 2026 |
-
"license": "Gemma License",
|
| 2027 |
-
"knowledge_cutoff": "2024/02"
|
| 2028 |
-
},
|
| 2029 |
-
"results": {
|
| 2030 |
-
"OVERALL": {
|
| 2031 |
-
"Average Score": 18.339626858215343,
|
| 2032 |
-
"Standard Deviation": 0.1553156123023995,
|
| 2033 |
-
"Rank": 43
|
| 2034 |
-
},
|
| 2035 |
-
"Geometry": {
|
| 2036 |
-
"Average Score": 0.244791417,
|
| 2037 |
-
"Standard Deviation": 0.0289612078,
|
| 2038 |
-
"Rank": 37
|
| 2039 |
-
},
|
| 2040 |
-
"Algebra": {
|
| 2041 |
-
"Average Score": 0.250614794,
|
| 2042 |
-
"Standard Deviation": 0.01991678295,
|
| 2043 |
-
"Rank": 38
|
| 2044 |
-
},
|
| 2045 |
-
"Probability": {
|
| 2046 |
-
"Average Score": 18.066869704202595,
|
| 2047 |
-
"Standard Deviation": null,
|
| 2048 |
-
"Rank": 48
|
| 2049 |
-
},
|
| 2050 |
-
"Logical": {
|
| 2051 |
-
"Average Score": 22.446113532575186,
|
| 2052 |
-
"Standard Deviation": 1.1759308097806727,
|
| 2053 |
-
"Rank": 43
|
| 2054 |
-
},
|
| 2055 |
-
"Social": {
|
| 2056 |
-
"Average Score": 0.202138025,
|
| 2057 |
-
"Standard Deviation": 0.02098346639,
|
| 2058 |
-
"Rank": 39
|
| 2059 |
-
},
|
| 2060 |
-
"Chemistry": {
|
| 2061 |
-
"Average Score": 27.195166540671735,
|
| 2062 |
-
"Standard Deviation": null,
|
| 2063 |
-
"Rank": 43
|
| 2064 |
-
},
|
| 2065 |
-
"CPP": {
|
| 2066 |
-
"Average Score": 28.014658234926813,
|
| 2067 |
-
"Standard Deviation": null,
|
| 2068 |
-
"Rank": 39
|
| 2069 |
-
}
|
| 2070 |
-
}
|
| 2071 |
-
},
|
| 2072 |
-
{
|
| 2073 |
-
"config": {
|
| 2074 |
-
"model_name": "mistral-7b-instruct-2",
|
| 2075 |
-
"organization": "Mistral",
|
| 2076 |
-
"license": "Apache 2.0",
|
| 2077 |
-
"knowledge_cutoff": "2023/12"
|
| 2078 |
-
},
|
| 2079 |
-
"results": {
|
| 2080 |
-
"OVERALL": {
|
| 2081 |
-
"Average Score": 32.27919528900069,
|
| 2082 |
-
"Standard Deviation": 2.070593349377193,
|
| 2083 |
-
"Rank": 28
|
| 2084 |
-
},
|
| 2085 |
-
"Geometry": {
|
| 2086 |
-
"Average Score": 0.216402626,
|
| 2087 |
-
"Standard Deviation": 0.03338414918,
|
| 2088 |
-
"Rank": 38
|
| 2089 |
-
},
|
| 2090 |
-
"Algebra": {
|
| 2091 |
-
"Average Score": 0.233777838,
|
| 2092 |
-
"Standard Deviation": 0.0155226054,
|
| 2093 |
-
"Rank": 40
|
| 2094 |
-
},
|
| 2095 |
-
"Probability": {
|
| 2096 |
-
"Average Score": 25.70261650740474,
|
| 2097 |
-
"Standard Deviation": null,
|
| 2098 |
-
"Rank": 45
|
| 2099 |
-
},
|
| 2100 |
-
"Logical": {
|
| 2101 |
-
"Average Score": 26.165635051797608,
|
| 2102 |
-
"Standard Deviation": 1.5009510944001014,
|
| 2103 |
-
"Rank": 41
|
| 2104 |
-
},
|
| 2105 |
-
"Social": {
|
| 2106 |
-
"Average Score": 0.209386782,
|
| 2107 |
-
"Standard Deviation": 0.02738569921,
|
| 2108 |
-
"Rank": 38
|
| 2109 |
-
},
|
| 2110 |
-
"Chemistry": {
|
| 2111 |
-
"Average Score": 30.70773868184025,
|
| 2112 |
-
"Standard Deviation": null,
|
| 2113 |
-
"Rank": 39
|
| 2114 |
-
},
|
| 2115 |
-
"CPP": {
|
| 2116 |
-
"Average Score": 31.382959631870822,
|
| 2117 |
-
"Standard Deviation": null,
|
| 2118 |
-
"Rank": 35
|
| 2119 |
-
}
|
| 2120 |
-
}
|
| 2121 |
-
},
|
| 2122 |
-
{
|
| 2123 |
-
"config": {
|
| 2124 |
-
"model_name": "mistral-7b-instruct-1",
|
| 2125 |
-
"organization": "Mistral",
|
| 2126 |
-
"license": "Apache 2.0",
|
| 2127 |
-
"knowledge_cutoff": "2023/12"
|
| 2128 |
-
},
|
| 2129 |
-
"results": {
|
| 2130 |
-
"OVERALL": {
|
| 2131 |
-
"Average Score": 14.750363553682964,
|
| 2132 |
-
"Standard Deviation": 0.442399072321264,
|
| 2133 |
-
"Rank": 48
|
| 2134 |
-
},
|
| 2135 |
-
"Geometry": {
|
| 2136 |
-
"Average Score": 0.161799938,
|
| 2137 |
-
"Standard Deviation": 0.03595278559,
|
| 2138 |
-
"Rank": 44
|
| 2139 |
-
},
|
| 2140 |
-
"Algebra": {
|
| 2141 |
-
"Average Score": 0.210341624,
|
| 2142 |
-
"Standard Deviation": 0.01736539119,
|
| 2143 |
-
"Rank": 41
|
| 2144 |
-
},
|
| 2145 |
-
"Probability": {
|
| 2146 |
-
"Average Score": 24.69501890202338,
|
| 2147 |
-
"Standard Deviation": null,
|
| 2148 |
-
"Rank": 46
|
| 2149 |
-
},
|
| 2150 |
-
"Logical": {
|
| 2151 |
-
"Average Score": 15.957706802740889,
|
| 2152 |
-
"Standard Deviation": 2.080778273455708,
|
| 2153 |
-
"Rank": 50
|
| 2154 |
-
},
|
| 2155 |
-
"Social": {
|
| 2156 |
-
"Average Score": 0.117646827,
|
| 2157 |
-
"Standard Deviation": 0.009321202779,
|
| 2158 |
-
"Rank": 47
|
| 2159 |
-
},
|
| 2160 |
-
"Chemistry": {
|
| 2161 |
-
"Average Score": 18.375111202411667,
|
| 2162 |
-
"Standard Deviation": null,
|
| 2163 |
-
"Rank": 47
|
| 2164 |
-
},
|
| 2165 |
-
"CPP": {
|
| 2166 |
-
"Average Score": 18.929093202755805,
|
| 2167 |
-
"Standard Deviation": null,
|
| 2168 |
-
"Rank": 42
|
| 2169 |
-
}
|
| 2170 |
-
}
|
| 2171 |
-
},
|
| 2172 |
-
{
|
| 2173 |
-
"config": {
|
| 2174 |
-
"model_name": "vicuna-13b",
|
| 2175 |
-
"organization": "LMSYS",
|
| 2176 |
-
"license": "Non-commercial",
|
| 2177 |
-
"knowledge_cutoff": "2023/07"
|
| 2178 |
-
},
|
| 2179 |
-
"results": {
|
| 2180 |
-
"OVERALL": {
|
| 2181 |
-
"Average Score": 13.302607436757697,
|
| 2182 |
-
"Standard Deviation": 0.570272227659312,
|
| 2183 |
-
"Rank": 50
|
| 2184 |
-
},
|
| 2185 |
-
"Geometry": {
|
| 2186 |
-
"Average Score": 0.200941928,
|
| 2187 |
-
"Standard Deviation": 0.03366817781,
|
| 2188 |
-
"Rank": 41
|
| 2189 |
-
},
|
| 2190 |
-
"Algebra": {
|
| 2191 |
-
"Average Score": 0.196123323,
|
| 2192 |
-
"Standard Deviation": 0.0135715643,
|
| 2193 |
-
"Rank": 42
|
| 2194 |
-
},
|
| 2195 |
-
"Probability": {
|
| 2196 |
-
"Average Score": 15.08476669604627,
|
| 2197 |
-
"Standard Deviation": null,
|
| 2198 |
-
"Rank": 50
|
| 2199 |
-
},
|
| 2200 |
-
"Logical": {
|
| 2201 |
-
"Average Score": 16.548339412104294,
|
| 2202 |
-
"Standard Deviation": 3.443370777556759,
|
| 2203 |
-
"Rank": 49
|
| 2204 |
-
},
|
| 2205 |
-
"Social": {
|
| 2206 |
-
"Average Score": 0.124655135,
|
| 2207 |
-
"Standard Deviation": 0.01122382671,
|
| 2208 |
-
"Rank": 46
|
| 2209 |
-
},
|
| 2210 |
-
"Chemistry": {
|
| 2211 |
-
"Average Score": 21.201173318496842,
|
| 2212 |
-
"Standard Deviation": null,
|
| 2213 |
-
"Rank": 45
|
| 2214 |
-
},
|
| 2215 |
-
"CPP": {
|
| 2216 |
-
"Average Score": 21.840013221590294,
|
| 2217 |
-
"Standard Deviation": null,
|
| 2218 |
-
"Rank": 40
|
| 2219 |
-
}
|
| 2220 |
-
}
|
| 2221 |
-
},
|
| 2222 |
-
{
|
| 2223 |
-
"config": {
|
| 2224 |
-
"model_name": "zephyr-7b-beta",
|
| 2225 |
-
"organization": "HuggingFace",
|
| 2226 |
-
"license": "MIT",
|
| 2227 |
-
"knowledge_cutoff": "2023/10"
|
| 2228 |
-
},
|
| 2229 |
-
"results": {
|
| 2230 |
-
"OVERALL": {
|
| 2231 |
-
"Average Score": 7.378234886105356,
|
| 2232 |
-
"Standard Deviation": 1.1456147261693999,
|
| 2233 |
-
"Rank": 51
|
| 2234 |
-
},
|
| 2235 |
-
"Geometry": {
|
| 2236 |
-
"Average Score": 0.114005544,
|
| 2237 |
-
"Standard Deviation": 0.03144354365,
|
| 2238 |
-
"Rank": 45
|
| 2239 |
-
},
|
| 2240 |
-
"Algebra": {
|
| 2241 |
-
"Average Score": 0.141766633,
|
| 2242 |
-
"Standard Deviation": 0.03179520129,
|
| 2243 |
-
"Rank": 43
|
| 2244 |
-
},
|
| 2245 |
-
"Probability": {
|
| 2246 |
-
"Average Score": 8.92696070171298,
|
| 2247 |
-
"Standard Deviation": null,
|
| 2248 |
-
"Rank": 53
|
| 2249 |
-
},
|
| 2250 |
-
"Logical": {
|
| 2251 |
-
"Average Score": 6.971377981442089,
|
| 2252 |
-
"Standard Deviation": 0.31669853263737413,
|
| 2253 |
-
"Rank": 55
|
| 2254 |
-
},
|
| 2255 |
-
"Social": {
|
| 2256 |
-
"Average Score": 0.0,
|
| 2257 |
-
"Standard Deviation": 0.0,
|
| 2258 |
-
"Rank": 52
|
| 2259 |
-
},
|
| 2260 |
-
"Chemistry": {
|
| 2261 |
-
"Average Score": 18.374948840997902,
|
| 2262 |
-
"Standard Deviation": null,
|
| 2263 |
-
"Rank": 47
|
| 2264 |
-
},
|
| 2265 |
-
"CPP": {
|
| 2266 |
-
"Average Score": 18.92902220864132,
|
| 2267 |
-
"Standard Deviation": null,
|
| 2268 |
-
"Rank": 43
|
| 2269 |
-
}
|
| 2270 |
-
}
|
| 2271 |
-
},
|
| 2272 |
-
{
|
| 2273 |
-
"config": {
|
| 2274 |
-
"model_name": "gemma-1.1-2b-it",
|
| 2275 |
-
"organization": "Google",
|
| 2276 |
-
"license": "Gemma License",
|
| 2277 |
-
"knowledge_cutoff": "2024/02"
|
| 2278 |
-
},
|
| 2279 |
-
"results": {
|
| 2280 |
-
"OVERALL": {
|
| 2281 |
-
"Average Score": 16.083251992757752,
|
| 2282 |
-
"Standard Deviation": 0.7340624884005772,
|
| 2283 |
-
"Rank": 46
|
| 2284 |
-
},
|
| 2285 |
-
"Geometry": {
|
| 2286 |
-
"Average Score": 0.183974034,
|
| 2287 |
-
"Standard Deviation": 0.0215548886,
|
| 2288 |
-
"Rank": 43
|
| 2289 |
-
},
|
| 2290 |
-
"Algebra": {
|
| 2291 |
-
"Average Score": 0.13422252,
|
| 2292 |
-
"Standard Deviation": 0.01922819511,
|
| 2293 |
-
"Rank": 44
|
| 2294 |
-
},
|
| 2295 |
-
"Probability": {
|
| 2296 |
-
"Average Score": 9.992136776217318,
|
| 2297 |
-
"Standard Deviation": null,
|
| 2298 |
-
"Rank": 52
|
| 2299 |
-
},
|
| 2300 |
-
"Logical": {
|
| 2301 |
-
"Average Score": 9.537233946101678,
|
| 2302 |
-
"Standard Deviation": 0.7567112693269967,
|
| 2303 |
-
"Rank": 53
|
| 2304 |
-
},
|
| 2305 |
-
"Social": {
|
| 2306 |
-
"Average Score": 0.167796727,
|
| 2307 |
-
"Standard Deviation": 0.01666541942,
|
| 2308 |
-
"Rank": 42
|
| 2309 |
-
},
|
| 2310 |
-
"Chemistry": {
|
| 2311 |
-
"Average Score": 20.11834233400297,
|
| 2312 |
-
"Standard Deviation": null,
|
| 2313 |
-
"Rank": 46
|
| 2314 |
-
},
|
| 2315 |
-
"CPP": {
|
| 2316 |
-
"Average Score": 20.724691953843916,
|
| 2317 |
-
"Standard Deviation": null,
|
| 2318 |
-
"Rank": 41
|
| 2319 |
-
}
|
| 2320 |
-
}
|
| 2321 |
-
},
|
| 2322 |
-
{
|
| 2323 |
-
"config": {
|
| 2324 |
-
"model_name": "llama2-7b-chat",
|
| 2325 |
-
"organization": "Meta",
|
| 2326 |
-
"license": "Llama 2 Community",
|
| 2327 |
-
"knowledge_cutoff": "2023/07"
|
| 2328 |
-
},
|
| 2329 |
-
"results": {
|
| 2330 |
-
"OVERALL": {
|
| 2331 |
-
"Average Score": 17.319161859655946,
|
| 2332 |
-
"Standard Deviation": 0.495520710612214,
|
| 2333 |
-
"Rank": 45
|
| 2334 |
-
},
|
| 2335 |
-
"Geometry": {
|
| 2336 |
-
"Average Score": 0.087067276,
|
| 2337 |
-
"Standard Deviation": 0.04274343402,
|
| 2338 |
-
"Rank": 46
|
| 2339 |
-
},
|
| 2340 |
-
"Algebra": {
|
| 2341 |
-
"Average Score": 0.12308805,
|
| 2342 |
-
"Standard Deviation": 0.01856053622,
|
| 2343 |
-
"Rank": 45
|
| 2344 |
-
},
|
| 2345 |
-
"Probability": {
|
| 2346 |
-
"Average Score": 8.860911732515305,
|
| 2347 |
-
"Standard Deviation": null,
|
| 2348 |
-
"Rank": 54
|
| 2349 |
-
},
|
| 2350 |
-
"Logical": {
|
| 2351 |
-
"Average Score": 18.812132126028335,
|
| 2352 |
-
"Standard Deviation": 3.0846832107977433,
|
| 2353 |
-
"Rank": 47
|
| 2354 |
-
},
|
| 2355 |
-
"Social": {
|
| 2356 |
-
"Average Score": 0.152905272,
|
| 2357 |
-
"Standard Deviation": 0.007166957097,
|
| 2358 |
-
"Rank": 43
|
| 2359 |
-
},
|
| 2360 |
-
"Chemistry": {
|
| 2361 |
-
"Average Score": 15.270334671133512,
|
| 2362 |
-
"Standard Deviation": null,
|
| 2363 |
-
"Rank": 50
|
| 2364 |
-
},
|
| 2365 |
-
"CPP": {
|
| 2366 |
-
"Average Score": 15.730513733660898,
|
| 2367 |
-
"Standard Deviation": null,
|
| 2368 |
-
"Rank": 45
|
| 2369 |
-
}
|
| 2370 |
-
}
|
| 2371 |
-
},
|
| 2372 |
-
{
|
| 2373 |
-
"config": {
|
| 2374 |
-
"model_name": "gemma-2b-it",
|
| 2375 |
-
"organization": "Google",
|
| 2376 |
-
"license": "Gemma License",
|
| 2377 |
-
"knowledge_cutoff": "2024/02"
|
| 2378 |
-
},
|
| 2379 |
-
"results": {
|
| 2380 |
-
"OVERALL": {
|
| 2381 |
-
"Average Score": 15.029602991101632,
|
| 2382 |
-
"Standard Deviation": 0.4529017602377039,
|
| 2383 |
-
"Rank": 47
|
| 2384 |
-
},
|
| 2385 |
-
"Geometry": {
|
| 2386 |
-
"Average Score": 0.198571153,
|
| 2387 |
-
"Standard Deviation": 0.01699161031,
|
| 2388 |
-
"Rank": 42
|
| 2389 |
-
},
|
| 2390 |
-
"Algebra": {
|
| 2391 |
-
"Average Score": 0.109883009,
|
| 2392 |
-
"Standard Deviation": 0.01520005833,
|
| 2393 |
-
"Rank": 46
|
| 2394 |
-
},
|
| 2395 |
-
"Probability": {
|
| 2396 |
-
"Average Score": 6.561360414966015,
|
| 2397 |
-
"Standard Deviation": null,
|
| 2398 |
-
"Rank": 56
|
| 2399 |
-
},
|
| 2400 |
-
"Logical": {
|
| 2401 |
-
"Average Score": 3.9858662356708785,
|
| 2402 |
-
"Standard Deviation": 0.5609499073366407,
|
| 2403 |
-
"Rank": 56
|
| 2404 |
-
},
|
| 2405 |
-
"Social": {
|
| 2406 |
-
"Average Score": 0.087452913,
|
| 2407 |
-
"Standard Deviation": 0.008170146562,
|
| 2408 |
-
"Rank": 50
|
| 2409 |
-
},
|
| 2410 |
-
"Chemistry": {
|
| 2411 |
-
"Average Score": 16.766144078336097,
|
| 2412 |
-
"Standard Deviation": null,
|
| 2413 |
-
"Rank": 49
|
| 2414 |
-
},
|
| 2415 |
-
"CPP": {
|
| 2416 |
-
"Average Score": 17.2715657115764,
|
| 2417 |
-
"Standard Deviation": null,
|
| 2418 |
-
"Rank": 44
|
| 2419 |
-
}
|
| 2420 |
-
}
|
| 2421 |
-
},
|
| 2422 |
-
{
|
| 2423 |
-
"config": {
|
| 2424 |
-
"model_name": "llama2-13b-chat",
|
| 2425 |
-
"organization": "Meta",
|
| 2426 |
-
"license": "Llama 2 Community",
|
| 2427 |
-
"knowledge_cutoff": "2023/07"
|
| 2428 |
-
},
|
| 2429 |
-
"results": {
|
| 2430 |
-
"OVERALL": {
|
| 2431 |
-
"Average Score": 17.47902371074294,
|
| 2432 |
-
"Standard Deviation": 0.4047581815962028,
|
| 2433 |
-
"Rank": 44
|
| 2434 |
-
},
|
| 2435 |
-
"Geometry": {
|
| 2436 |
-
"Average Score": 0.072729954,
|
| 2437 |
-
"Standard Deviation": 0.02315988261,
|
| 2438 |
-
"Rank": 48
|
| 2439 |
-
},
|
| 2440 |
-
"Algebra": {
|
| 2441 |
-
"Average Score": 0.080371692,
|
| 2442 |
-
"Standard Deviation": 0.01277569453,
|
| 2443 |
-
"Rank": 47
|
| 2444 |
-
},
|
| 2445 |
-
"Probability": {
|
| 2446 |
-
"Average Score": 12.738302754764042,
|
| 2447 |
-
"Standard Deviation": null,
|
| 2448 |
-
"Rank": 51
|
| 2449 |
-
},
|
| 2450 |
-
"Logical": {
|
| 2451 |
-
"Average Score": 21.708359515217182,
|
| 2452 |
-
"Standard Deviation": 1.4862481594434973,
|
| 2453 |
-
"Rank": 45
|
| 2454 |
-
},
|
| 2455 |
-
"Social": {
|
| 2456 |
-
"Average Score": 0.149125922,
|
| 2457 |
-
"Standard Deviation": 0.01157416827,
|
| 2458 |
-
"Rank": 44
|
| 2459 |
-
},
|
| 2460 |
-
"Chemistry": {
|
| 2461 |
-
"Average Score": 12.786967781868814,
|
| 2462 |
-
"Standard Deviation": null,
|
| 2463 |
-
"Rank": 53
|
| 2464 |
-
},
|
| 2465 |
-
"CPP": {
|
| 2466 |
-
"Average Score": 13.17258252933903,
|
| 2467 |
-
"Standard Deviation": null,
|
| 2468 |
-
"Rank": 48
|
| 2469 |
-
}
|
| 2470 |
-
}
|
| 2471 |
-
},
|
| 2472 |
-
{
|
| 2473 |
-
"config": {
|
| 2474 |
-
"model_name": "vicuna-7b",
|
| 2475 |
-
"organization": "LMSYS",
|
| 2476 |
-
"license": "Non-commercial",
|
| 2477 |
-
"knowledge_cutoff": "2023/07"
|
| 2478 |
-
},
|
| 2479 |
-
"results": {
|
| 2480 |
-
"OVERALL": {
|
| 2481 |
-
"Average Score": 13.31896682669754,
|
| 2482 |
-
"Standard Deviation": 0.30441157156016124,
|
| 2483 |
-
"Rank": 49
|
| 2484 |
-
},
|
| 2485 |
-
"Geometry": {
|
| 2486 |
-
"Average Score": 0.083457058,
|
| 2487 |
-
"Standard Deviation": 0.02520989111,
|
| 2488 |
-
"Rank": 47
|
| 2489 |
-
},
|
| 2490 |
-
"Algebra": {
|
| 2491 |
-
"Average Score": 0.070883882,
|
| 2492 |
-
"Standard Deviation": 0.007315853253,
|
| 2493 |
-
"Rank": 48
|
| 2494 |
-
},
|
| 2495 |
-
"Probability": {
|
| 2496 |
-
"Average Score": 8.255246380068842,
|
| 2497 |
-
"Standard Deviation": null,
|
| 2498 |
-
"Rank": 55
|
| 2499 |
-
},
|
| 2500 |
-
"Logical": {
|
| 2501 |
-
"Average Score": 10.046676845257544,
|
| 2502 |
-
"Standard Deviation": 0.6816182835206797,
|
| 2503 |
-
"Rank": 52
|
| 2504 |
-
},
|
| 2505 |
-
"Social": {
|
| 2506 |
-
"Average Score": 0.111076414,
|
| 2507 |
-
"Standard Deviation": 0.004805626512,
|
| 2508 |
-
"Rank": 48
|
| 2509 |
-
},
|
| 2510 |
-
"Chemistry": {
|
| 2511 |
-
"Average Score": 13.838150481781991,
|
| 2512 |
-
"Standard Deviation": null,
|
| 2513 |
-
"Rank": 51
|
| 2514 |
-
},
|
| 2515 |
-
"CPP": {
|
| 2516 |
-
"Average Score": 14.255194156624162,
|
| 2517 |
-
"Standard Deviation": null,
|
| 2518 |
-
"Rank": 46
|
| 2519 |
-
}
|
| 2520 |
-
}
|
| 2521 |
-
},
|
| 2522 |
-
{
|
| 2523 |
-
"config": {
|
| 2524 |
-
"model_name": "koala-13b",
|
| 2525 |
-
"organization": "UC Berkeley",
|
| 2526 |
-
"license": "Non-commercial",
|
| 2527 |
-
"knowledge_cutoff": "2023/04"
|
| 2528 |
-
},
|
| 2529 |
-
"results": {
|
| 2530 |
-
"OVERALL": {
|
| 2531 |
-
"Average Score": 6.419305623111718,
|
| 2532 |
-
"Standard Deviation": 0.19611070515647736,
|
| 2533 |
-
"Rank": 53
|
| 2534 |
-
},
|
| 2535 |
-
"Geometry": {
|
| 2536 |
-
"Average Score": 0.017374001,
|
| 2537 |
-
"Standard Deviation": 0.01747053557,
|
| 2538 |
-
"Rank": 49
|
| 2539 |
-
},
|
| 2540 |
-
"Algebra": {
|
| 2541 |
-
"Average Score": 0.018129197,
|
| 2542 |
-
"Standard Deviation": 0.01054371383,
|
| 2543 |
-
"Rank": 49
|
| 2544 |
-
},
|
| 2545 |
-
"Probability": {
|
| 2546 |
-
"Average Score": 4.1717283559090035,
|
| 2547 |
-
"Standard Deviation": null,
|
| 2548 |
-
"Rank": 57
|
| 2549 |
-
},
|
| 2550 |
-
"Logical": {
|
| 2551 |
-
"Average Score": 7.484701131693112,
|
| 2552 |
-
"Standard Deviation": 0.172417770163525,
|
| 2553 |
-
"Rank": 54
|
| 2554 |
-
},
|
| 2555 |
-
"Social": {
|
| 2556 |
-
"Average Score": 0.096983835,
|
| 2557 |
-
"Standard Deviation": 0.007847059783,
|
| 2558 |
-
"Rank": 49
|
| 2559 |
-
},
|
| 2560 |
-
"Chemistry": {
|
| 2561 |
-
"Average Score": 6.177985738164252,
|
| 2562 |
-
"Standard Deviation": null,
|
| 2563 |
-
"Rank": 54
|
| 2564 |
-
},
|
| 2565 |
-
"CPP": {
|
| 2566 |
-
"Average Score": 6.36433272373514,
|
| 2567 |
-
"Standard Deviation": null,
|
| 2568 |
-
"Rank": 49
|
| 2569 |
-
}
|
| 2570 |
-
}
|
| 2571 |
-
},
|
| 2572 |
-
{
|
| 2573 |
-
"config": {
|
| 2574 |
-
"model_name": "openassistant-pythia-12b",
|
| 2575 |
-
"organization": "OpenAssistant",
|
| 2576 |
-
"license": "Non-commercial",
|
| 2577 |
-
"knowledge_cutoff": "2023/04"
|
| 2578 |
-
},
|
| 2579 |
-
"results": {
|
| 2580 |
-
"OVERALL": {
|
| 2581 |
-
"Average Score": 0.0,
|
| 2582 |
-
"Standard Deviation": 0.0,
|
| 2583 |
-
"Rank": 54
|
| 2584 |
-
},
|
| 2585 |
-
"Geometry": {
|
| 2586 |
-
"Average Score": 0.0,
|
| 2587 |
-
"Standard Deviation": 0.0,
|
| 2588 |
-
"Rank": 50
|
| 2589 |
-
},
|
| 2590 |
-
"Algebra": {
|
| 2591 |
-
"Average Score": 0.0,
|
| 2592 |
-
"Standard Deviation": 0.0,
|
| 2593 |
-
"Rank": 50
|
| 2594 |
-
},
|
| 2595 |
-
"Probability": {
|
| 2596 |
-
"Average Score": 0.0,
|
| 2597 |
-
"Standard Deviation": null,
|
| 2598 |
-
"Rank": 58
|
| 2599 |
-
},
|
| 2600 |
-
"Logical": {
|
| 2601 |
-
"Average Score": 0.0,
|
| 2602 |
-
"Standard Deviation": 0.0,
|
| 2603 |
-
"Rank": 57
|
| 2604 |
-
},
|
| 2605 |
-
"Social": {
|
| 2606 |
-
"Average Score": 0.030792528,
|
| 2607 |
-
"Standard Deviation": 0.007518796391,
|
| 2608 |
-
"Rank": 51
|
| 2609 |
-
},
|
| 2610 |
-
"Chemistry": {
|
| 2611 |
-
"Average Score": 0.0,
|
| 2612 |
-
"Standard Deviation": null,
|
| 2613 |
-
"Rank": 55
|
| 2614 |
-
},
|
| 2615 |
-
"CPP": {
|
| 2616 |
-
"Average Score": 0.0,
|
| 2617 |
-
"Standard Deviation": null,
|
| 2618 |
-
"Rank": 50
|
| 2619 |
-
}
|
| 2620 |
-
}
|
| 2621 |
-
},
|
| 2622 |
-
{
|
| 2623 |
-
"config": {
|
| 2624 |
-
"model_name": "nemotron-70b",
|
| 2625 |
-
"organization": "NVIDIA",
|
| 2626 |
-
"license": "Unknown",
|
| 2627 |
-
"knowledge_cutoff": "Unknown"
|
| 2628 |
-
},
|
| 2629 |
-
"results": {
|
| 2630 |
-
"OVERALL": {
|
| 2631 |
-
"Average Score": 100.0,
|
| 2632 |
-
"Standard Deviation": 0.0,
|
| 2633 |
-
"Rank": 1
|
| 2634 |
-
},
|
| 2635 |
-
"Chemistry": {
|
| 2636 |
-
"Average Score": 96.00601450276388,
|
| 2637 |
-
"Standard Deviation": null,
|
| 2638 |
-
"Rank": 3
|
| 2639 |
-
},
|
| 2640 |
-
"Logical": {
|
| 2641 |
-
"Average Score": 98.08807085219765,
|
| 2642 |
-
"Standard Deviation": 0.832489959144682,
|
| 2643 |
-
"Rank": 5
|
| 2644 |
-
},
|
| 2645 |
-
"Probability": {
|
| 2646 |
-
"Average Score": 91.16755514126538,
|
| 2647 |
-
"Standard Deviation": null,
|
| 2648 |
-
"Rank": 4
|
| 2649 |
-
}
|
| 2650 |
-
}
|
| 2651 |
-
},
|
| 2652 |
-
{
|
| 2653 |
-
"config": {
|
| 2654 |
-
"model_name": "llama-3.2-3b-it",
|
| 2655 |
-
"organization": "Meta",
|
| 2656 |
-
"license": "Llama 3 Community",
|
| 2657 |
-
"knowledge_cutoff": "Unknown"
|
| 2658 |
-
},
|
| 2659 |
-
"results": {
|
| 2660 |
-
"OVERALL": {
|
| 2661 |
-
"Average Score": 30.40742747938681,
|
| 2662 |
-
"Standard Deviation": 1.6816556668351852,
|
| 2663 |
-
"Rank": 30
|
| 2664 |
-
},
|
| 2665 |
-
"Chemistry": {
|
| 2666 |
-
"Average Score": 27.43049468475638,
|
| 2667 |
-
"Standard Deviation": null,
|
| 2668 |
-
"Rank": 42
|
| 2669 |
-
},
|
| 2670 |
-
"Logical": {
|
| 2671 |
-
"Average Score": 41.58905844173492,
|
| 2672 |
-
"Standard Deviation": 5.2798221527591,
|
| 2673 |
-
"Rank": 29
|
| 2674 |
-
},
|
| 2675 |
-
"Probability": {
|
| 2676 |
-
"Average Score": 62.02868227997844,
|
| 2677 |
-
"Standard Deviation": null,
|
| 2678 |
-
"Rank": 18
|
| 2679 |
-
}
|
| 2680 |
-
}
|
| 2681 |
-
},
|
| 2682 |
-
{
|
| 2683 |
-
"config": {
|
| 2684 |
-
"model_name": "yi-lightning",
|
| 2685 |
-
"organization": "01 AI",
|
| 2686 |
-
"license": "Proprietary",
|
| 2687 |
-
"knowledge_cutoff": "Unknown"
|
| 2688 |
-
},
|
| 2689 |
-
"results": {
|
| 2690 |
-
"Chemistry": {
|
| 2691 |
-
"Average Score": 100.0,
|
| 2692 |
-
"Standard Deviation": null,
|
| 2693 |
-
"Rank": 1
|
| 2694 |
-
},
|
| 2695 |
-
"Logical": {
|
| 2696 |
-
"Average Score": 98.816765663456,
|
| 2697 |
-
"Standard Deviation": 0.3271335810663529,
|
| 2698 |
-
"Rank": 3
|
| 2699 |
-
},
|
| 2700 |
-
"Probability": {
|
| 2701 |
-
"Average Score": 95.8842044402052,
|
| 2702 |
-
"Standard Deviation": null,
|
| 2703 |
-
"Rank": 2
|
| 2704 |
-
}
|
| 2705 |
-
}
|
| 2706 |
-
},
|
| 2707 |
-
{
|
| 2708 |
-
"config": {
|
| 2709 |
-
"model_name": "glm-4-plus",
|
| 2710 |
-
"organization": "Zhipu AI",
|
| 2711 |
-
"license": "Proprietary",
|
| 2712 |
-
"knowledge_cutoff": "Unknown"
|
| 2713 |
-
},
|
| 2714 |
-
"results": {
|
| 2715 |
-
"Chemistry": {
|
| 2716 |
-
"Average Score": 99.05822908668402,
|
| 2717 |
-
"Standard Deviation": null,
|
| 2718 |
-
"Rank": 2
|
| 2719 |
-
},
|
| 2720 |
-
"Logical": {
|
| 2721 |
-
"Average Score": 99.45307787995229,
|
| 2722 |
-
"Standard Deviation": 0.5982476107949444,
|
| 2723 |
-
"Rank": 1
|
| 2724 |
-
},
|
| 2725 |
-
"Probability": {
|
| 2726 |
-
"Average Score": 92.04426702796823,
|
| 2727 |
-
"Standard Deviation": null,
|
| 2728 |
-
"Rank": 3
|
| 2729 |
-
}
|
| 2730 |
-
}
|
| 2731 |
-
}
|
| 2732 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
src/results/{models_2024-10-20-23:34:57.242641.json → models_2024-10-24-08:08:59.127307.json}
RENAMED
|
The diff for this file is too large to render.
See raw diff
|
|
|