Calibration on TruthfulQA
2.132Gain
S
Updated 2d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.04 | 2.132 | 4 | - | - | |
2026.04 | 2.073 | 3 | - | - | |
2026.04 | 2.014 | 0 | - | - | |
2026.04 | 2.01 | 1 | - | - | |
2026.04 | 1.984 | 0 | - | - | |
2026.04 | 1.936 | 0 | - | - | |
2026.04 | 1.901 | 0 | - | - | |
2026.04 | 1.896 | 0 | - | - | |
2026.04 | 1.48 | 2 | - | - | |
2026.04 | 1.464 | 0 | - | - | |
2026.04 | 1.433 | 2 | - | - | |
2026.04 | 1.416 | 0 | - | - | |
2026.04 | 1.008 | 0 | - | - | |
2026.04 | 0.994 | 0 | - | - | |
2026.04 | 0.981 | 0 | - | - | |
2026.04 | 0.974 | 0 | - | - | |
2026.04 | 0.954 | 0 | - | - | |
2026.04 | 0.924 | 0 | - | - | |
2026.04 | 0.886 | 0 | - | - | |
2026.04 | 0.796 | 0 | - | - | |
2026.04 | 0.776 | 0 | - | - | |
2026.04 | 0.226 | 1 | - | - | |
2026.04 | 0.11 | 1 | - | - | |
2026.04 | 0.076 | 0 | - | - | |
2026.04 | 0.053 | 1 | - | - | |
2026.04 | 0 | 0 | - | - | |
2026.04 | 0 | 0 | - | - | |
2026.04 | 0 | 0 | - | - | |
2026.04 | 0 | 1 | - | - | |
2026.04 | -0.554 | 0 | - | - | |
2026.04 | -0.651 | 0 | - | - | |
2026.04 | -0.909 | 0 | - | - | |
2026.05 | - | - | 25.23 | 71.16 | |
2026.05 | - | - | 9.82 | 71.16 | |
2026.05 | - | - | 8.47 | 70.45 | |
| - | - | 8.41 | 70.83 | ||
2026.05 | - | - | 54.88 | 78.5 | |
2026.05 | - | - | 54.52 | 78.48 | |
2026.05 | - | - | 52.87 | 78.24 | |
2026.05 | - | - | 10.28 | 66.81 | |
2026.05 | - | - | 33.66 | 63.75 | |
2026.05 | - | - | 6.99 | 71.93 | |
2026.05 | - | - | 6.5 | 79.66 |