Hallucination Detection on GSM8K (Comprehensive Metrics)
80.62AUROC
HALLUGUARD
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.01 | 80.62 | 77.3 | 80.22 | 76.88 | 68.21 | |
2026.01 | 79.01 | 76.73 | 79.1 | 74.25 | 67.92 | |
2026.01 | 77.1 | 74 | 76.2 | 69.5 | 59.8 | |
2026.01 | 75.81 | 74.68 | 82.55 | 78.91 | 70.45 | |
2026.01 | 75.4 | 72.3 | 74 | 67.1 | 59.1 | |
2026.01 | 74.2 | 70.6 | 67.1 | 60.8 | 50.1 | |
2026.01 | 73.9 | 71.2 | 76.5 | 70.1 | 60.7 | |
2026.01 | 73.4 | 69.8 | 64.9 | 57.9 | 48.3 | |
2026.01 | 73 | 69.1 | 66.1 | 58.4 | 49.5 | |
2026.01 | 72.57 | 70.31 | 74.91 | 69.14 | 62.1 | |
2026.01 | 72.5 | 69.2 | 69.4 | 62.5 | 52.3 | |
2026.01 | 72.1 | 68.5 | 64.2 | 56.6 | 48 | |
2026.01 | 72.04 | 69.88 | 78.33 | 74.11 | 65.42 | |
2026.01 | 71.2 | 67.9 | 67.8 | 60.3 | 50.4 | |
2026.01 | 70.8 | 67.2 | 71.8 | 64.1 | 56.3 | |
2026.01 | 69.2 | 66.1 | 70.1 | 62 | 54.4 | |
2026.01 | 69 | 65.4 | 69.2 | 61.5 | 51.9 | |
2026.01 | 68.1 | 64.3 | 67.5 | 59.2 | 49.8 | |
2026.01 | 66.8 | 63 | 64.5 | 56.2 | 48.7 | |
2026.01 | 65.4 | 61.5 | 62.4 | 54.1 | 46.2 |