Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Jailbreak Evaluation on AdvBench, HarmBench, and StrongReject

10.8Time per Successful Attack (s)

AGR

-247.9681,498.7163,245.44,992.084May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
10.8
2026.05
24.8
2026.05
30.5
2026.05
34
2026.05
132
2026.05
838.4
2026.05
6,480