List your company

Long-term state poisoning evaluation on OpenClaw Log Replay

4.34Harm Score (HS)Kimi k2.5
4.28444.65975.0355.4103May 7, 2026

Evaluation results

MethodLinks
Kimi k2.52026.054.34
Grok-12026.054.8
GPT-4o2026.055.03
MiniMax-abab6.52026.055.73