Safety Evaluation on AdvBench (Harmfulness Rate by Step)
0Reasoning Harmfulness Rate
RealSafe-R1
Updated 27d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.08 | 0 | 0 | - | |
2025.08 | 0 | 2 | - | |
2025.08 | 0 | 0 | - | |
2025.08 | 0 | 2 | - | |
2025.08 | 0 | 0 | - | |
2025.08 | 0 | 40 | - | |
2025.08 | 0 | 0 | - | |
2025.08 | 0 | 0 | - | |
2025.08 | 0 | 0 | - | |
2025.08 | 1.02 | 1 | - | |
2025.08 | 1.08 | 1.28 | - | |
2025.08 | 1.1 | 1 | - | |
2025.08 | 1.12 | 1.02 | - | |
2025.08 | 1.14 | 1 | - | |
2025.08 | 1.14 | 1 | - | |
2025.08 | 1.18 | 1.08 | - | |
2025.08 | 1.2 | 1.04 | - | |
2025.08 | 1.22 | 1 | - | |
2025.08 | 1.22 | 1 | - | |
2025.08 | 1.24 | 1 | - | |
2025.08 | 1.24 | 1.03 | - | |
2025.08 | 1.3 | 1.12 | - | |
2025.08 | 1.32 | 1.02 | - | |
2025.08 | 1.33 | 1 | - | |
2025.08 | 1.36 | 1.12 | - | |
2025.08 | 1.39 | 1.07 | - | |
2025.08 | 1.4 | 1.02 | - | |
2025.08 | 1.47 | 1.29 | - | |
2025.08 | 1.48 | 1.14 | - | |
2025.08 | 1.5 | 1 | - | |
2025.08 | 1.53 | 1.13 | - | |
2025.08 | 1.58 | 1.08 | - | |
2025.08 | 1.66 | 1 | - | |
2025.08 | 1.71 | 1.22 | - | |
2025.08 | 2 | 2 | - | |
2025.08 | 2 | 4 | - | |
2025.08 | 2.02 | 1.46 | - | |
2025.08 | 2.28 | 1.3 | - | |
2025.08 | 2.32 | 1.5 | - | |
2025.08 | 6 | 6 | - | |
2025.08 | 6 | 2 | - | |
2025.08 | 12 | 6 | - | |
2025.08 | 14 | 14 | - | |
2025.08 | 26 | 22 | - | |
2025.08 | 28 | 24 | - | |
2025.08 | 30 | 20 | - | |
2025.08 | 30 | 28 | - | |
2025.08 | 38 | 40 | - | |
2025.08 | 40 | 32 | - | |
2025.08 | 40 | 40 | - | |
2025.08 | - | - | 42 | |
2025.08 | - | - | 0 | |
2025.08 | - | - | 0 | |
2025.08 | - | - | 20 | |
2025.08 | - | - | 2 | |
2025.08 | - | - | 18 | |
2025.08 | - | - | 0 | |
2025.08 | - | - | 4 | |
2025.08 | - | - | 0 | |
2025.08 | - | - | 22 | |
2025.08 | - | - | 0 | |
2025.08 | - | - | 14 | |
2025.08 | - | - | 0 | |
2025.08 | - | - | 10 | |
2025.08 | - | - | 0 | |
2025.08 | - | - | 2 | |
2025.08 | - | - | 0 |