Agent Safety Judgment on ROME Implicit Risks 1.0 (IR)
86.81F1-Score
ARISE (Std)
Updated 28d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 86.81 | |
2026.05 | 82.47 | |
2026.05 | 80.2 | |
2026.05 | 76.09 | |
2026.05 | 72.88 | |
2026.05 | 69.23 | |
2026.05 | 67.88 | |
2026.05 | 66.67 | |
2026.05 | 66 | |
2026.05 | 65.2 | |
2026.05 | 63.47 | |
2026.05 | 61.79 | |
2026.05 | 57.72 | |
2026.05 | 55.71 | |
2026.05 | 52.38 | |
2026.05 | 50.44 | |
2026.05 | 49.4 | |
2026.05 | 42.86 | |
2026.05 | 42.53 | |
2026.05 | 41.63 | |
2026.05 | 36.19 | |
2026.05 | 31.46 | |
2026.05 | 27.03 | |
2026.05 | 24.1 |