Hallucination Detection on M-HalDetect (val)
89.98A-ROC
VIB-Probe
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 89.98 | 82.35 | |
2026.01 | 88.36 | 81.23 | |
2026.01 | 88.13 | 80.2 | |
2026.01 | 86.71 | 80.41 | |
2026.01 | 86.51 | 78.87 | |
2026.01 | 85.17 | 80.79 | |
2026.01 | 84.82 | 80.4 | |
2026.01 | 84.76 | 78.52 | |
2026.01 | 83.33 | 77.26 | |
2026.01 | 82.02 | 71.14 | |
2026.01 | 81.23 | 73.56 | |
2026.01 | 80.92 | 71.13 | |
2026.01 | 79.58 | 74.62 | |
2026.01 | 78.93 | 70.78 | |
2026.01 | 78.42 | 70.54 | |
2026.01 | 78.21 | 70.04 | |
2026.01 | 77.38 | 71.2 | |
2026.01 | 77.28 | 69.13 | |
2026.01 | 77.18 | 69.8 | |
2026.01 | 75.19 | 69.3 | |
2026.01 | 66.47 | 42.71 | |
2026.01 | 63.52 | 41.39 | |
2026.01 | 60.21 | 40.36 | |
2026.01 | 59.92 | 40.39 | |
2026.01 | 59.01 | 39.54 | |
2026.01 | 56.9 | 38.5 | |
2026.01 | 55.9 | 37.52 | |
2026.01 | 54.9 | 38.22 | |
2026.01 | 54 | 38.93 | |
2026.01 | 53.27 | 36.87 |