Alignment Prediction on OpinionQA
60.4Reg Accuracy
Default
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 60.4 | 59 | 58.5 | 59.7 | 57.9 | 52.9 | 58.2 | 53.8 | 57.5 | |
2026.02 | 60.2 | 57.2 | 55.1 | 58.2 | 52.7 | 42.9 | 44.5 | 54.6 | 53.2 | |
2026.02 | 59.9 | 58.3 | 52.8 | 60.3 | 57.2 | 55.7 | 58.9 | 58.8 | 57.8 | |
2026.02 | 59.6 | 58.3 | 58.6 | 58 | 56 | 61.1 | 58.8 | 58.4 | 58.6 | |
2026.02 | 59.6 | 56.6 | 60.1 | 59.3 | 59.3 | 61.3 | 59.2 | 59.7 | 59.4 | |
2026.02 | 59.4 | 61.5 | 60.2 | 55.4 | 54.3 | 61.1 | 59.3 | 61.7 | 59.1 | |
2026.02 | 59.2 | 55.6 | 54.5 | 56.3 | 54.1 | 56 | 56.6 | 58.1 | 56.3 | |
2026.02 | 57.4 | 57.6 | 58.6 | 59.4 | 58.8 | 59 | 57.7 | 57.5 | 58.2 | |
2026.02 | 57 | 58.2 | 56.3 | 54.9 | 51.9 | 58.5 | 57 | 58.1 | 56.5 | |
2026.02 | 49.1 | 47.6 | 46.9 | 48 | 47.7 | 48.2 | 47.8 | 45.8 | 47.7 | |
2026.02 | 44.9 | 41.9 | 41.4 | 43.4 | 42.1 | 44.3 | 44.1 | 40.9 | 43.2 | |
2026.02 | 38.8 | 41.6 | 40.2 | 36.6 | 36.4 | 39.9 | 41.1 | 38 | 39.3 |