Ranking on MTBench
1Correlation CoefficientBayesian
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Bayesian2025.05 | 1 | 100 | |
| Single Judge2025.05 | 0.971 | 83.3 | |
| Bootstrap2025.05 | 0.943 | 100 | |
| Bradley-Terry2025.05 | 0.943 | 100 | |
| Simple Average2025.05 | 0.943 | 66.7 |
| Method | Links | ||
|---|---|---|---|
| Bayesian2025.05 | 1 | 100 | |
| Single Judge2025.05 | 0.971 | 83.3 | |
| Bootstrap2025.05 | 0.943 | 100 | |
| Bradley-Terry2025.05 | 0.943 | 100 | |
| Simple Average2025.05 | 0.943 | 66.7 |