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

Jailbreak Attack Defense on Mousetrap

22.7FFR (Reasoning)

Paraphrase

-0.9085.22111.3517.479Aug 6, 2025
Updated 27d ago

Evaluation Results

MethodLinks
2025.08
22.761.4
2025.08
18.263.6
2025.08
11.445.5
2025.08
11.452.3
2025.08
11.459.1
2025.08
9.175
2025.08
9.154.5
2025.08
7.363.6
2025.08
6.836.4
2025.08
536.4
2025.08
4.590.9
2025.08
2.345.5
2025.08
2.359.1
2025.08
2.318.2
2025.08
2.356.5
2025.08
2.338.6
2025.08
018.2