LLM Agent Task Completion on AgentDojo No Attack
73.91Benign Utility
IPIGuard
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 73.91 | |
2026.03 | 67.39 | |
2026.03 | 66.3 | |
2026.03 | 61.96 | |
2026.03 | 57.61 | |
2026.03 | 56.52 | |
2026.03 | 56.52 | |
2026.03 | 56.52 | |
2026.03 | 54.35 | |
2026.03 | 54.35 | |
2026.03 | 54.35 | |
2026.03 | 54.35 | |
2026.03 | 53.26 | |
2026.03 | 51.09 | |
2026.03 | 45.65 | |
2026.03 | 40.22 | |
2026.03 | 38.04 | |
2026.03 | 38.04 | |
2026.03 | 36.96 | |
2026.03 | 36.96 | |
2026.03 | 34.78 | |
2026.03 | 32.61 |