Long-term state poisoning evaluation on OpenClaw ZH
3.82Harm Score (HS)GPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.05 | 3.82 | |
| Grok-12026.05 | 4.94 | |
| Kimi k2.52026.05 | 4.98 | |
| MiniMax-abab6.52026.05 | 5.96 |
| Method | Links | |
|---|---|---|
| GPT-4o2026.05 | 3.82 | |
| Grok-12026.05 | 4.94 | |
| Kimi k2.52026.05 | 4.98 | |
| MiniMax-abab6.52026.05 | 5.96 |