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

Jailbreak Attack Evaluation on Do-Not-Answer

2.5ASR

Gemini 2.5 Flash

2.045.1458.2511.355Jan 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
2.5
2026.01
3
2026.01
3
2026.01
4
2026.01
4.5
2026.01
14