Pairwise Preference Prediction on DyCoBench-1K Single Criterion
70.2P(A > B)
DYCORM(OURS)
Updated 8d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 70.2 | 68.5 | 59.2 | 69.7 | |
2026.05 | 59.3 | 58 | 56.7 | 58.8 | |
2026.05 | 58.9 | 58.1 | 57.6 | 58.4 | |
2026.05 | 58.2 | 56.9 | 50.6 | 57.7 | |
2026.05 | 54.8 | 53.5 | 47.2 | 54.3 | |
2026.05 | 54.1 | 52.8 | 46.5 | 53.6 | |
2026.05 | 53.4 | 52.1 | 45.8 | 52.9 | |
2026.05 | 53.2 | 51.9 | 45.6 | 52.7 | |
2026.05 | 52.9 | 51.6 | 45.3 | 52.4 | |
2026.05 | 51.6 | 50.3 | 44 | 51.1 | |
2026.05 | 51.3 | 50 | 43.7 | 50.8 | |
2026.05 | 51 | 49.7 | 43.4 | 50.5 | |
2026.05 | 50.8 | 49.5 | 43.2 | 50.3 | |
2026.05 | 49.5 | 48.2 | 41.9 | 49 | |
2026.05 | 49.3 | 48 | 41.7 | 48.8 | |
2026.05 | 48.9 | 47.6 | 41.3 | 48.4 | |
2026.05 | 48.6 | 47.3 | 41 | 48.1 |