Mathematical Reasoning on AMC12 (Best-of-64 accuracy)
58.66Best-of-64 AccuracyMSV64
Evaluation Results
| Method | Links | |
|---|---|---|
| MSV64Best-of-K=642026.03 | 58.66 | |
| PRM-7BBest-of-K=64, Backbone=Qwen2.5-Math-7B2026.03 | 52.24 | |
| PRM-7B + WVBest-of-K=64, Backbone=Qwen2.5-Math-7B, Weighted Voting=true2026.03 | 50 |