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

Jailbreak Robustness on StrongREJECT PAIR

76.65Goodness Score

REFLECTOR

27.998840.629453.2665.8906May 20, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.05
76.65
2026.05
45.5
2026.05
44.41
2026.05
40.34
31.95
29.87