Long-term state poisoning evaluation on OpenClaw Routine
3.9Harm Score (HS)Grok-1
Evaluation Results
| Method | Links | |
|---|---|---|
| Grok-12026.05 | 3.9 | |
| Kimi k2.52026.05 | 4.52 | |
| GPT-4o2026.05 | 5.47 | |
| MiniMax-abab6.52026.05 | 6.66 |
| Method | Links | |
|---|---|---|
| Grok-12026.05 | 3.9 | |
| Kimi k2.52026.05 | 4.52 | |
| GPT-4o2026.05 | 5.47 | |
| MiniMax-abab6.52026.05 | 6.66 |