Jailbreak Attack on AutoDAN T-R
0ASRGPT-5.2
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.2Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.04 | 0 | |
| GPT-5.4*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target2026.04 | 0 | |
| o4-mini*Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Frontier dev target2026.04 | 11 | |
| Kimi-K2.5Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.04 | 13 | |
| Grok 4Model Category=Frontier, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.04 | 14 | |
| Phi-4-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.04 | 16 | |
| Grok 3†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.04 | 18 | |
| GPT-4.1-miniModel Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=Held-out2026.04 | 25 | |
| DeepSeek-V3.2†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.04 | 26 | |
| GPT-4o†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.04 | 31 | |
| GPT-4.1†Model Category=Standard, Evaluation Protocol=Three-judge majority vote, Development Status=AR-Standard dev target2026.04 | 35 |