Update README.md

README.md

@@ -88,12 +88,12 @@ Following is the mG-Pass@16 results of Qwen2.5-72B-Instruct-as-Judge and LiveMat
 | Qwen2.5-Math-7B-Instruct | 37.91 | 39.54 |
 | Llama-3.1-8B-Instruct | 10.43 | 9.29 |
 | Llama-3.1-70B-Instruct | 21.37 | 22.12 |
-| Llama-3.3-70B-Instruct | 27.36 | 27.23 |
-| Mistral-Large-Instruct-2411 | 36.66 | 37.54 |
-| Qwen2.5-32B-Instruct | 39.09 | 39.44 |
-| Qwen2.5-72B-Instruct | 38.52 | 39.01 |
+| Llama-3.3-70B-Instruct | 27.36 | 30.47 |
+| Mistral-Large-Instruct-2411 | 36.66 | 36.67 |
+| Qwen2.5-32B-Instruct | 39.09 | 37.84 |
+| Qwen2.5-72B-Instruct | 38.52 | 37.57 |
 | deepseek-math-7b-rl | 14.01 | 14.13 |
-| Qwen2.5-Math-72B-Instruct | 43.80 | 43.17 |
+| Qwen2.5-Math-72B-Instruct | 43.80 | 42.10 |
 
 ## Related Citation
 ```