List your company

Jailbreak Attack on AUTORISE Frontier

52ASRDeepSeek-V3.2†
6.7618.50530.2541.995Apr 23, 2026

Evaluation results

MethodLinks
DeepSeek-V3.2†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target, Independent evaluation runs=32026.0452
Grok 3†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target, Independent evaluation runs=32026.0444.5
Grok 4Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out, Independent evaluation runs=32026.0444.5
GPT-4.1-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out, Independent evaluation runs=32026.0443.5
GPT-4.1†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target, Independent evaluation runs=32026.0442
Phi-4-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out, Independent evaluation runs=32026.0441.5
GPT-4o†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target, Independent evaluation runs=32026.0440.5
Kimi-K2.5Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out, Independent evaluation runs=32026.0440.5
o4-mini*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target, Independent evaluation runs=32026.0426.8
GPT-5.4*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target, Independent evaluation runs=32026.0412.2
GPT-5.2Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out, Independent evaluation runs=32026.048.5