Update README.md
Browse files
README.md
CHANGED
@@ -27,8 +27,7 @@ For a deeper look into the implementation details, refer to the our repository:
|
|
27 |
|
28 |
We used the [EvalScope](https://github.com/modelscope/evalscope) to evaluate models and report Pass@1 accuracy across all benchmarks. The number of responses generated per problem is as follows:
|
29 |
- 64 responses: `AMC23, AIME24, AIME25`
|
30 |
-
-
|
31 |
-
- 4 responses: `Math500, Olympiad-Bench, Vietnamese-Entrance-Math-Exam`
|
32 |
- 1 responses: `IFEval`
|
33 |
|
34 |
Sampling Configs:
|
|
|
27 |
|
28 |
We used the [EvalScope](https://github.com/modelscope/evalscope) to evaluate models and report Pass@1 accuracy across all benchmarks. The number of responses generated per problem is as follows:
|
29 |
- 64 responses: `AMC23, AIME24, AIME25`
|
30 |
+
- 4 responses: `Math500, Olympiad-Bench, Vietnamese-Entrance-Math-Exam, Minerva-Math, Math-Gaokao-2023-English`
|
|
|
31 |
- 1 responses: `IFEval`
|
32 |
|
33 |
Sampling Configs:
|