Upload eval_results/mattshumer/Reflection-Llama-3.1-70B/main/mixeval_hard/results_2024-09-06T14-02-20.json with huggingface_hub
Browse files
eval_results/mattshumer/Reflection-Llama-3.1-70B/main/mixeval_hard/results_2024-09-06T14-02-20.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overall score (final score)": 0.5835,
|
| 3 |
+
"MATH": 0.869,
|
| 4 |
+
"BBH": 0.981,
|
| 5 |
+
"DROP": 0.853,
|
| 6 |
+
"GSM8k": 0.855,
|
| 7 |
+
"AGIEval": 0.394,
|
| 8 |
+
"TriviaQA": 0.696,
|
| 9 |
+
"MBPP": 0.0,
|
| 10 |
+
"MMLU": 0.385,
|
| 11 |
+
"HellaSwag": 0.328,
|
| 12 |
+
"BoolQ": 0.459,
|
| 13 |
+
"GPQA": 0.25,
|
| 14 |
+
"PIQA": 0.5,
|
| 15 |
+
"OpenBookQA": 0.625,
|
| 16 |
+
"ARC": 0.5,
|
| 17 |
+
"CommonsenseQA": 0.36,
|
| 18 |
+
"SIQA": 0.55
|
| 19 |
+
}
|