Long-term state poisoning evaluation on OpenClaw EN
3.76Harm Score (HS)Grok-1
Evaluation Results
| Method | Links | |
|---|---|---|
| Grok-12026.05 | 3.76 | |
| Kimi k2.52026.05 | 3.86 | |
| MiniMax-abab6.52026.05 | 6.87 | |
| GPT-4o2026.05 | 7.23 |
| Method | Links | |
|---|---|---|
| Grok-12026.05 | 3.76 | |
| Kimi k2.52026.05 | 3.86 | |
| MiniMax-abab6.52026.05 | 6.87 | |
| GPT-4o2026.05 | 7.23 |