Uncertainty Estimation on NQ-open
88.67A1 Accuracy
EigV+MCH
Updated 3d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.05 | 88.67 | 23.93 | 93.82 | 34.88 | 73.6 | |
2025.05 | 88.02 | 32.52 | 91.53 | 46.9 | 75.88 | |
2025.05 | 86.08 | 26.99 | 89.93 | 39.54 | 71.81 | |
2025.05 | 80.91 | 27.61 | 91.76 | 35.27 | 69.44 | |
2025.05 | 79.61 | 40.49 | 86.72 | 50 | 69.77 | |
2025.05 | 78.64 | 32.52 | 87.18 | 42.64 | 68.96 | |
2025.05 | 77.35 | 33.75 | 91.53 | 36.05 | 67.49 | |
2025.05 | 77.35 | 20.25 | 90.16 | 34.5 | 66.82 | |
2025.05 | 77.02 | 25.76 | 89.47 | 40.31 | 67.09 | |
2025.05 | 76.05 | 37.42 | 83.75 | 51.93 | 69.85 | |
2025.05 | 75.73 | 23.31 | 87.18 | 37.98 | 67.37 | |
2025.05 | 66.02 | 47.24 | 77.57 | 55.43 | 67.21 | |
2025.05 | 65.37 | 12.88 | 88.56 | 24.42 | 63.94 | |
2025.05 | 61.49 | 44.17 | 76.43 | 53.88 | 65.38 | |
2025.05 | 61.49 | 9.82 | 83.06 | 18.99 | 63.57 | |
2025.05 | 60.19 | 47.85 | 77.35 | 51.16 | 64.87 |