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

Safety Evaluation on English Safety Evaluation

57.5Offensive Attack Success Rate

AceGPT-7B-chat

20.47630.08839.749.312Jun 24, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
57.550.7
2026.06
54.839.7
2026.06
53.417.8
2026.06
42.517.8
2026.06
268.2
2026.06
21.90