Ranking on Omni-MATH
79.1CorrelationBayesian
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Bayesian2025.05 | 79.1 | 73.7 | |
| Bootstrap2025.05 | 76.7 | 36.8 | |
| Bradley-Terry2025.05 | 76.7 | 36.8 | |
| Simple Average2025.05 | 76.7 | 22.8 | |
| Single Judge2025.05 | 72.5 | 22.8 |
| Method | Links | ||
|---|---|---|---|
| Bayesian2025.05 | 79.1 | 73.7 | |
| Bootstrap2025.05 | 76.7 | 36.8 | |
| Bradley-Terry2025.05 | 76.7 | 36.8 | |
| Simple Average2025.05 | 76.7 | 22.8 | |
| Single Judge2025.05 | 72.5 | 22.8 |