List your company

Mathematical Reasoning on DEEPMATH 128 samples

35.93Top-1 AccuracyePF
9.118816.079423.0430.0006Oct 7, 2025

Evaluation results

MethodLinks
ePFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-7B-Instruct2025.1035.93
PFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-7B-Instruct2025.1034.37
Best-of-NSelection=Argmax, Scoring=ORM, Base Model=Qwen2.5-7B-Instruct2025.1032.03
Beam-SearchSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-7B-Instruct2025.1032.03
Self-ConsistencySelection=MV, Base Model=Qwen2.5-7B-Instruct2025.1030.46
ePFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-1.5B-Instruct2025.1025
Base SamplingBase Model=Qwen2.5-7B-Instruct2025.1023.43
PFSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-1.5B-Instruct2025.1022.65
Beam-SearchSelection=Argmax, Scoring=PRM, Base Model=Qwen2.5-1.5B-Instruct2025.1021.09
Best-of-NSelection=Argmax, Scoring=ORM, Base Model=Qwen2.5-1.5B-Instruct2025.1020.31
Self-ConsistencySelection=MV, Base Model=Qwen2.5-1.5B-Instruct2025.1013.28
Base SamplingBase Model=Qwen2.5-1.5B-Instruct2025.1010.15