Mathematical Reasoning on AMO-Bench VeRA-H / VeRA-H Pro
31.75Avg@5 Accuracy (Seeds)Frontier Models (Mean)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Frontier Models (Mean)Model count=16, Seeds count=50, Verified variants count (H / Pro)=244 / 502026.01 | 31.75 | 42.97 | 38.38 |