List your company

Mathematical Reasoning on MATH500 (128-sample random subset)

71.09Top-1 AccuracyePF
44.278851.239458.265.1606Oct 7, 2025

Evaluation results

MethodLinks
ePFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-7B-Instruct2025.1071.09
PFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-7B-Instruct2025.1070.31
Best-of-NSelection=Argmax, Scoring=ORM, Base Model=Qwen2.5-7B-Instruct2025.1067.96
ePFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-1.5B-Instruct2025.1066.42
Beam-SearchSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-7B-Instruct2025.1066.4
Self-ConsistencySelection=MV, Base Model=Qwen2.5-7B-Instruct2025.1065.62
Beam-SearchSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-1.5B-Instruct2025.1062.5
Base SamplingBase Model=Qwen2.5-7B-Instruct2025.1060.93
PFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-1.5B-Instruct2025.1060.15
Best-of-NSelection=Argmax, Scoring=ORM, Base Model=Qwen2.5-1.5B-Instruct2025.1057.81
Self-ConsistencySelection=MV, Base Model=Qwen2.5-1.5B-Instruct2025.1053.9
Base SamplingBase Model=Qwen2.5-1.5B-Instruct2025.1045.31