Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Content Safety Detection on WildJailbreak (F1, ASR)
Loading...
96.6
F1 Score
prompt–response verification framework
92.648
93.674
94.7
95.726
Jun 24, 2026
F1 Score
ASR
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
ASR
prompt–response verification framework
2026.06
96.6
3.4
prompt–response verification framework
2026.06
96.5
3.5
AutoDefense / SelfDefend
Type=Strongest Applica...
2026.06
93.6
-
AutoDefense / SelfDefend
Type=Strongest Applica...
2026.06
92.8
-
Feedback
Search any
task
Search any
task