Hallucination detection on MMLU-Pro
69.81Accuracy
LEAP
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.11 | 69.81 | - | 75.31 | |
2025.11 | 64.23 | - | 71.18 | |
2025.11 | 63.21 | - | 71.15 | |
2025.11 | 62.26 | - | 71.43 | |
2025.11 | 61.05 | - | 69.23 | |
2025.11 | 60.61 | - | 72.19 | |
2025.11 | 60.14 | - | 70.37 | |
2025.11 | 59.6 | - | 69.23 | |
2025.11 | 59.56 | - | 64.52 | |
2025.11 | 59.12 | - | 70.42 | |
2025.11 | 58.85 | - | 69.51 | |
2025.11 | 58.67 | - | 68.04 | |
2025.11 | 58.34 | - | 68.51 | |
2025.11 | 58.23 | - | 71.11 | |
2025.11 | 57.96 | - | 70.49 | |
2025.11 | 57.33 | - | 68 | |
2025.11 | 56.67 | - | 67.5 | |
2025.11 | 56.67 | - | 67.17 | |
2025.11 | 56.66 | - | 69.54 | |
2025.11 | 55.81 | - | 68.28 | |
2025.11 | 55.67 | - | 66.67 | |
2025.11 | 55.33 | - | 65.59 | |
2025.11 | 55.33 | - | 68.84 | |
2025.11 | 55.25 | - | 70.67 | |
2025.11 | 55 | - | 70.97 | |
2025.11 | 54.88 | - | 70.74 | |
2025.11 | 54.68 | - | 55 | |
2025.11 | 54.67 | - | 69.64 | |
2025.11 | 54.41 | - | 54.05 | |
2025.11 | 54.29 | - | 70.37 | |
2026.01 | - | 79.56 | - | |
2026.01 | - | 74.83 | - | |
2026.01 | - | 76.76 | - | |
2026.01 | - | 71.22 | - | |
2026.01 | - | 77.85 | - | |
2026.01 | - | 81.08 | - | |
2026.01 | - | 77.56 | - | |
2026.01 | - | 74.05 | - | |
2026.01 | - | 82.21 | - | |
2026.01 | - | 87.08 | - | |
2026.01 | - | 77.73 | - | |
2026.01 | - | 77.56 | - | |
2026.01 | - | 57.92 | - | |
2026.01 | - | 74.65 | - | |
2026.01 | - | 75.85 | - |