Helpfulness Preference Labeling Accuracy on Ultra-Real
74.8Benchmark Score
Few-Shot
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 74.8 | 57.3 | 17.5 | |
2026.02 | 74.1 | 56.5 | 17.6 | |
2026.02 | 73.4 | 57.2 | 16.2 | |
2026.02 | 73.4 | 61.1 | 12.3 | |
2026.02 | 73.4 | 59.7 | 13.7 | |
2026.02 | 73.2 | 52.4 | 20.8 | |
2026.02 | 72.9 | 61 | 11.9 | |
2026.02 | 72.8 | 61.9 | 10.9 | |
2026.02 | 72.1 | 53.9 | 18.2 | |
2026.02 | 71.9 | 57.9 | 14 | |
2026.02 | 71.9 | 54.1 | 17.8 | |
2026.02 | 71.6 | 62.1 | 9.5 | |
2026.02 | 71.5 | 64 | 7.5 | |
2026.02 | 70.2 | 63.5 | 6.7 | |
2026.02 | 69.1 | 58.3 | 10.8 |