Error Detection on Unanswerability hallucination detection benchmarks (Average)
75.1AUC
COMET
Updated 24d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 75.1 | 69.3 | 71 | |
2026.06 | 73.2 | 64.9 | 76.7 | |
2026.06 | 70.5 | 54 | 76.1 | |
2026.06 | 70.1 | 57.2 | 76.5 | |
2026.06 | 67.2 | 61.9 | 81.7 | |
2026.06 | 64.9 | 55.3 | 81.2 | |
2026.06 | 64.8 | 47.4 | 80 | |
2026.06 | 63.5 | 46.7 | 84.4 | |
2026.06 | 61.5 | 56 | 95.4 | |
2026.06 | 61.4 | 44.2 | 88.6 | |
2026.06 | 61.2 | 50.3 | 91.1 | |
2026.06 | 61 | 44.1 | 88.6 | |
2026.06 | 59.9 | 56.7 | 95.3 | |
2026.06 | 59.9 | 43.8 | 87.7 | |
2026.06 | 59.8 | 43.4 | 90.4 | |
2026.06 | 58.6 | 51.9 | 88.6 | |
2026.06 | 58.4 | 51.9 | 89.2 | |
2026.06 | 56.1 | 52.6 | 88.4 | |
2026.06 | 54.8 | 39.7 | 93 | |
2026.06 | 54.7 | 37.7 | 94.3 | |
2026.06 | 53.4 | 58.4 | 95.5 | |
2026.06 | 52.2 | 38 | 97.9 | |
2026.06 | 52.2 | 37.6 | 97.5 | |
2026.06 | 51.4 | 43.2 | 95 | |
2026.06 | 50.6 | 46.5 | 96.1 | |
2026.06 | 49.9 | 35.3 | 96.2 | |
2026.06 | 49.3 | 44.1 | 92.6 | |
2026.06 | 49.3 | 44.1 | 92.6 |