Trajectory-safety diagnosis on ATBench-F
49.2R.S. Score
Qwen2-7B-Instruct + FATE
Updated 21d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 49.2 | 18.4 | 43.1 | |
2026.05 | 46.8 | 16.5 | 40.6 | |
2026.05 | 33.6 | 13.5 | 30.2 | |
2026.05 | 29.5 | 12 | 26.8 | |
2026.05 | 24.8 | 12.6 | 18.5 | |
2026.05 | 18.4 | 8.3 | 15 | |
2026.05 | 15.8 | 9.4 | 22.9 | |
2026.05 | 7.7 | 3.6 | 6.8 | |
2026.05 | 7 | 11.6 | 26.6 | |
2026.05 | 6.6 | 3 | 8.2 | |
2026.05 | 6.2 | 5.8 | 15.5 | |
2026.05 | 5.3 | 6 | 15.5 | |
2026.05 | 4.4 | 8.2 | 18.3 | |
2026.05 | 1 | 9.6 | 21.2 |