Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Detection on MAS Qwen-2.5-7B (Lookahead)
Loading...
96.77
Accuracy
AgentLens
26.3204
44.6102
62.9
81.1898
Jun 21, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
AgentLens
Method Category=Interp...
2026.06
96.77
GPT-4o
Method Category=LLM-as...
2026.06
87.1
Claude Opus-4.6
Method Category=LLM-as...
2026.06
87.1
Claude Sonnet-4.6
Method Category=LLM-as...
2026.06
83.87
GPT-5.2
Method Category=LLM-as...
2026.06
64.52
Gemini-3-Pro
Method Category=LLM-as...
2026.06
35.48
Deepseek-V4-Flash
Method Category=LLM-as...
2026.06
35.48
Deepseek-V4-Pro
Method Category=LLM-as...
2026.06
29.03
Feedback
Search any
task
Search any
task