Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Content Safety Detection on HarmBench cyber
Loading...
92.8
F1 Score
prompt–response verification framework
85.312
87.256
89.2
91.144
Jun 24, 2026
F1 Score
Attack Success Rate (ASR)
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Attack Success Rate (ASR)
prompt–response verification framework
2026.06
92.8
4.7
Single-Agent+CoT
Type=Strongest Applica...
2026.06
85.6
-
Feedback
Search any
task
Search any
task
