Explainability classification on AEGIS 2.0 (test)
79.6Unsafe F1
LEG large
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 79.6 | - | |
2026.01 | 76.95 | - | |
2026.01 | 76.93 | - | |
2026.01 | 74.28 | - | |
2026.01 | 72.73 | - | |
2026.01 | 70.9 | - | |
2026.01 | 69.53 | - | |
2026.01 | 69.49 | - | |
2026.01 | 66.91 | - | |
2026.01 | 64.06 | - | |
2026.01 | 52.77 | - | |
2026.01 | 52.03 | - | |
2026.01 | 45.94 | - | |
2026.01 | 45.91 | - | |
2026.01 | 45.72 | - | |
2026.01 | 43.99 | - | |
2026.01 | 41.07 | - | |
2026.01 | 40.88 | - | |
2026.01 | 37.21 | - | |
2026.01 | 33.12 | - | |
2026.01 | 32.74 | - | |
2026.01 | 32.53 | - | |
2026.01 | 31.74 | - | |
2026.01 | 31.18 | - | |
2026.01 | 29.59 | - | |
2026.01 | 29.34 | - | |
2026.01 | 26.48 | - | |
2026.01 | - | 53.28 | |
2026.01 | - | 60.33 | |
2026.01 | - | 66.11 |