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

Jailbreak Detection on WJB

93.26ACC

gpt-5-mini

44.452857.123969.79582.4661Feb 14, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
93.26
2026.02
87.29
2026.02
86.65
2026.02
85.43
2026.02
83.03
2026.02
81.49
81.45
2026.02
79.23
2026.02
79.19
2026.02
69.46
68.51
2026.02
52.17
2026.02
46.33