Mathematical Reasoning on Omni-MATH (Best-of-64 Accuracy)
35.4Accuracy (Best-of-64)MSV64
Evaluation Results
| Method | Links | |
|---|---|---|
| MSV64Best-of-K=642026.03 | 35.4 | |
| PRM-7B + WVBest-of-K=64, Backbone=Qwen2.5-Math-7B, Weighted Voting=true2026.03 | 23.66 | |
| PRM-7BBest-of-K=64, Backbone=Qwen2.5-Math-7B2026.03 | 23.44 |