Update README.md

README.md

@@ -112,7 +112,7 @@ Since the compared PRMs have not been trained on code-related tasks, this sectio
 
 | Reward Model             | Method                  | MBPP  | MBPP+ | HumanEval | HumanEval+ | LiveCodeBench-2024.01-2024-11 |
 |--------------------------|-------------------------|-------|-------|-----------|------------|-------------------------------|
-| N/A                      | Greedy Sampling Pass@1 | 77.9  | 65.2  | **82.3**  | **78.7**   | 26.0                          |
+| N/A                      | Greedy Sampling Pass@1 | 79.9  | 65.9  | **82.9**  | **78.7**   | 26.0                          |
 | Skywork-o1-Open-PRM-7B   | Best-of-N@64           | **81.2** | **68.5** | 81.1      | 74.4       | **31.3**                      |