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

Jailbreaking on Adversarial Behaviors (test)

15ASR

AmpleGCG

11.6434.325779.68May 9, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
151113.6722.4618.5515.04
2026.05
241313.8722.8522.4619.34
2026.05
301324.832.0326.1728.13
2026.05
381229.331.0531.429.82
2026.05
842240.2843.2538.9236.52
2026.05
982146.4122.3421.3927.13
2026.05
982146.4122.3421.3927.13
2026.05
991543.2893.8495.190.62