Mathematical Problem Solving on Omni-MATH (Best-of-N accuracy)
35.4Best-of-N Accuracy
MSV 64
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 35.4 | |
2026.03 | 33.35 | |
2026.03 | 32.1 | |
2026.03 | 31.98 | |
2026.03 | 31.79 | |
2026.03 | 31.79 | |
2026.03 | 31.76 | |
2026.03 | 31.62 | |
2026.03 | 31.33 | |
2026.03 | 31.02 | |
2026.03 | 29.1 | |
2026.03 | 29 | |
2026.03 | 28.91 | |
2026.03 | 28.85 | |
2026.03 | 28.78 | |
2026.03 | 24.32 | |
2026.03 | 24.32 |