shenzhi-wang commited on
Commit
51f420f
Β·
verified Β·
1 Parent(s): d812772

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
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** πŸ”‘ | **86.1** (Top-1 among πŸ”‘) | (-1.5, 1.7) |
99
- | Qwen2.5-72B-Chat πŸ”‘ | 78.0 | (-1.8, 1.8) |
100
  | Athene-v2-Chat πŸ”‘ | 85.0 | (-1.4, 1.7) |
101
  | Llama-3.1-Nemotron-70B-Instruct πŸ”‘ | 84.9 | (-1.7, 1.8) |
102
  | Llama-3.1-405B-Instruct-FP8 πŸ”‘ | 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** πŸ”‘ | **72.4** (Top-1 Among πŸ”‘) | (-4.3, 4.1) |
118
- | Qwen2.5-72B-Chat πŸ”‘ | 63.3 | (-2.5, 2.3) |
119
  | Athene-v2-Chat πŸ”‘ | 72.1 | (-2.5, 2.5) |
120
  | Llama-3.1-Nemotron-70B-Instruct πŸ”‘ | 71.0 | (-2.8, 3.1) |
121
  | Llama-3.1-405B-Instruct-FP8 πŸ”‘ | 67.1 | (-2.2, 2.8) |
 
96
  | | Score | 95% CIs |
97
  | --------------------------------- | ------------------------ | ----------- |
98
  | **Xwen-72B-Chat** πŸ”‘ | **86.1** (Top-1 among πŸ”‘) | (-1.5, 1.7) |
99
+ | Qwen2.5-72B-Instruct πŸ”‘ | 78.0 | (-1.8, 1.8) |
100
  | Athene-v2-Chat πŸ”‘ | 85.0 | (-1.4, 1.7) |
101
  | Llama-3.1-Nemotron-70B-Instruct πŸ”‘ | 84.9 | (-1.7, 1.8) |
102
  | Llama-3.1-405B-Instruct-FP8 πŸ”‘ | 69.3 | (-2.4, 2.2) |
 
115
  | | Score | 95% CIs |
116
  | --------------------------------- | ------------------------ | ----------- |
117
  | **Xwen-72B-Chat** πŸ”‘ | **72.4** (Top-1 Among πŸ”‘) | (-4.3, 4.1) |
118
+ | Qwen2.5-72B-Instruct πŸ”‘ | 63.3 | (-2.5, 2.3) |
119
  | Athene-v2-Chat πŸ”‘ | 72.1 | (-2.5, 2.5) |
120
  | Llama-3.1-Nemotron-70B-Instruct πŸ”‘ | 71.0 | (-2.8, 3.1) |
121
  | Llama-3.1-405B-Instruct-FP8 πŸ”‘ | 67.1 | (-2.2, 2.8) |