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

Safety Evaluation on JailbreakBench

0Harmful Rate

SafeReAct

-1.8810.8123.536.19Mar 10, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.03
0--
2026.03
0--
2026.03
0--
2026.03
1--
2026.03
2--
2026.03
7--
2026.03
8--
2026.03
9--
2026.03
17--
2026.03
23--
2026.03
27--
2026.03
33--
2026.03
41--
2026.03
43--
2026.03
45--
2026.03
47--
2025.12
-99-
2025.12
-98-
2025.12
-99-
2025.12
-55-
2025.12
-78-
2025.12
-81-
2025.12
-82-
2025.12
-91-
2025.12
-90-
2025.12
-92-
2025.12
-86.87-
2025.12
-84-
2025.12
-99-
2026.03
--37.5
2026.03
--85.5
2026.03
--94
2026.03
-66-
2026.03
-6-