Update README.md
Browse files
README.md
CHANGED
@@ -96,7 +96,7 @@ All results below, except those for `Xwen-72B-Chat`, are sourced from [Arena-Har
|
|
96 |
| | Score | 95% CIs |
|
97 |
| --------------------------------- | ------------------------ | ----------- |
|
98 |
| **Xwen-72B-Chat** π | **86.1** (Top-1 among π) | (-1.5, 1.7) |
|
99 |
-
| Qwen2.5-72B-
|
100 |
| Athene-v2-Chat π | 85.0 | (-1.4, 1.7) |
|
101 |
| Llama-3.1-Nemotron-70B-Instruct π | 84.9 | (-1.7, 1.8) |
|
102 |
| Llama-3.1-405B-Instruct-FP8 π | 69.3 | (-2.4, 2.2) |
|
@@ -115,7 +115,7 @@ All results below, except those for `Xwen-72B-Chat`, are sourced from [Arena-Har
|
|
115 |
| | Score | 95% CIs |
|
116 |
| --------------------------------- | ------------------------ | ----------- |
|
117 |
| **Xwen-72B-Chat** π | **72.4** (Top-1 Among π) | (-4.3, 4.1) |
|
118 |
-
| Qwen2.5-72B-
|
119 |
| Athene-v2-Chat π | 72.1 | (-2.5, 2.5) |
|
120 |
| Llama-3.1-Nemotron-70B-Instruct π | 71.0 | (-2.8, 3.1) |
|
121 |
| Llama-3.1-405B-Instruct-FP8 π | 67.1 | (-2.2, 2.8) |
|
|
|
96 |
| | Score | 95% CIs |
|
97 |
| --------------------------------- | ------------------------ | ----------- |
|
98 |
| **Xwen-72B-Chat** π | **86.1** (Top-1 among π) | (-1.5, 1.7) |
|
99 |
+
| Qwen2.5-72B-Instruct π | 78.0 | (-1.8, 1.8) |
|
100 |
| Athene-v2-Chat π | 85.0 | (-1.4, 1.7) |
|
101 |
| Llama-3.1-Nemotron-70B-Instruct π | 84.9 | (-1.7, 1.8) |
|
102 |
| Llama-3.1-405B-Instruct-FP8 π | 69.3 | (-2.4, 2.2) |
|
|
|
115 |
| | Score | 95% CIs |
|
116 |
| --------------------------------- | ------------------------ | ----------- |
|
117 |
| **Xwen-72B-Chat** π | **72.4** (Top-1 Among π) | (-4.3, 4.1) |
|
118 |
+
| Qwen2.5-72B-Instruct π | 63.3 | (-2.5, 2.3) |
|
119 |
| Athene-v2-Chat π | 72.1 | (-2.5, 2.5) |
|
120 |
| Llama-3.1-Nemotron-70B-Instruct π | 71.0 | (-2.8, 3.1) |
|
121 |
| Llama-3.1-405B-Instruct-FP8 π | 67.1 | (-2.2, 2.8) |
|