Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-term state poisoning evaluation on OpenClaw Routine
Loading...
3.9
Harm Score (HS)
Grok-1
3.7896
4.5348
5.28
6.0252
May 7, 2026
Harm Score (HS)
Updated 23d ago
Evaluation Results
Method
Method
Links
Harm Score (HS)
Grok-1
2026.05
3.9
Kimi k2.5
2026.05
4.52
GPT-4o
2026.05
5.47
MiniMax-abab6.5
2026.05
6.66
Feedback
Search any
task
Search any
task