List your company
ResearchFormerly WizWand

Jailbreak Attack on TeleAI-Safety

1.1ASRGPT-5.4*
-0.128.11516.3524.585Apr 23, 2026
Updated 6mo ago

Evaluation results

MethodLinks
GPT-5.4*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target2026.041.1
GPT-5.2Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.041.4
o4-mini*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target2026.042.5
Kimi-K2.5Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.045.9
Grok 4Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.046.2
Phi-4-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.0411
GPT-4.1†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0413.3
GPT-4o†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0414.7
DeepSeek-V3.2†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0415.5
GPT-4.1-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.0415.8
Grok 3†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.0431.6