List your company

Jailbreak Attack on JBDistill-Bench

1.2Attack Success Rate (ASR)GPT-5.2
-0.62411.6882436.312Apr 23, 2026

Evaluation results

MethodLinks
GPT-5.2Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.041.2
GPT-5.4*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target2026.041.4
Grok 4Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.0410.6
o4-mini*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target2026.0410.6
Kimi-K2.5Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.0424.6
GPT-4o†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0436.2
GPT-4.1-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.0437
DeepSeek-V3.2†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0439.2
GPT-4.1†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0439.6
Phi-4-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.0441.6
Grok 3†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0446.8