Mathematical Reasoning on AIME24 (Avg@32, Pass@8, Dist-N, SemDiv)
23.54Avg@32CraEG
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CraEGModel=Hunyuan-1.8B-Instruct, Temperature=1, Top-p=12026.01 | 23.54 | 39.94 | 79.41 | 18.81 | |
| Standard SamplingModel=Hunyuan-1.8B-Instruct, Temperature=1, Top-p=12026.01 | 22.18 | 35.01 | 81.54 | 19.27 |