Agent Perturbation Reliability Testing on AgentHarm
90.6Accuracy
GPT-4o
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 90.6 | 9.4 | 6.3 | 12.5 | |
2026.03 | 90.6 | 9.4 | 6.3 | 12.5 | |
2026.03 | 90.6 | 9.4 | 6.3 | 12.5 | |
2026.03 | 81.3 | 18.8 | 6.3 | 31.3 | |
2026.03 | 81.3 | 18.8 | 25 | 12.5 |