Hallucination Detection on GSM8K (test)
79.01AUROC (Reference)
HALLUGUARD
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 79.01 | 76.73 | 64.38 | 64.97 | |
2026.01 | 77.33 | 73.97 | 60.48 | 61.26 | |
2026.01 | 75.89 | 72.83 | 62.29 | 63.46 | |
2026.01 | 75.79 | 76.26 | 60.91 | 59.77 | |
2026.01 | 75.2 | 72.9 | 63.62 | 61.79 | |
2026.01 | 74.61 | 68.35 | 58.57 | 62.58 | |
2026.01 | 73.73 | 67.51 | 56.02 | 57.28 | |
2026.01 | 72.3 | 72.26 | 54.49 | 58.39 | |
2026.01 | 68.35 | 66.66 | 50.41 | 51.16 | |
2026.01 | 68.22 | 66.05 | 53.03 | 53.21 | |
2026.01 | 68.06 | 65.09 | 52.99 | 50.89 | |
2026.01 | 67.08 | 65.6 | 53.66 | 55.12 | |
2026.01 | 66.9 | 64.81 | 50.47 | 55.36 | |
2026.01 | 66.57 | 65.55 | 48.84 | 53.4 | |
2026.01 | 66.41 | 63.44 | 52.05 | 53.57 | |
2026.01 | 66.23 | 64.1 | 53.52 | 52.31 | |
2026.01 | 65.95 | 63.63 | 54.95 | 48.25 | |
2026.01 | 65.88 | 63.4 | 48.28 | 48.17 | |
2026.01 | 65.8 | 63.7 | 52.12 | 54.07 | |
2026.01 | 65.72 | 62.01 | 54.49 | 50.34 | |
2026.01 | 65.69 | 61.95 | 53.69 | 46.06 | |
2026.01 | 65.27 | 62.94 | 52.8 | 46.6 | |
2026.01 | 64.49 | 61.47 | 53.28 | 47.55 | |
2026.01 | 64.32 | 62.81 | 51.15 | 51.3 | |
2026.01 | 64.2 | 61.96 | 50.15 | 45.35 | |
2026.01 | 63.83 | 60.2 | 54.43 | 44.82 | |
2026.01 | 63.37 | 62.33 | 53.53 | 49.94 | |
2026.01 | 63.29 | 59.87 | 53.17 | 50.02 | |
2026.01 | 63.27 | 59.41 | 47.42 | 47.38 | |
2026.01 | 62.72 | 59.09 | 49.33 | 44.35 | |
2026.01 | 62.59 | 58.88 | 47.21 | 42.2 | |
2026.01 | 61.81 | 60.46 | 44.5 | 44.76 | |
2026.01 | 61.49 | 59.55 | 51.63 | 51.45 | |
2026.01 | 61.31 | 58.9 | 45.83 | 40.86 | |
2026.01 | 60.99 | 57.54 | 49.28 | 44.43 | |
2026.01 | 60.96 | 58.67 | 46.27 | 47.44 | |
2026.01 | 60.63 | 57.01 | 46.22 | 40.24 | |
2026.01 | 60.16 | 58.14 | 47.73 | 49.49 | |
2026.01 | 59.84 | 55.85 | 44.05 | 39.49 | |
2026.01 | 59.79 | 56.52 | 50.31 | 42.23 | |
2026.01 | 59.45 | 55.95 | 43.04 | 44.08 | |
2026.01 | 58.15 | 54.71 | 43.65 | 36.71 | |
2026.01 | 57.98 | 54.58 | 46.72 | 39.86 | |
2026.01 | 57.95 | 54.68 | 42.78 | 41.95 | |
2026.01 | 57.61 | 53.63 | 41.37 | 41.59 | |
2026.01 | 57.58 | 56.07 | 43.39 | 38.94 | |
2026.01 | 56.69 | 53.71 | 45.78 | 39.52 | |
2026.01 | 55.76 | 54.17 | 44.91 | 43.18 |