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

Harmful Refusal on DAN

94.9ASR

Qwen2.5-3B-IT

7.22829.98952.7575.511Jun 9, 2025Aug 3, 2025Sep 28, 2025Nov 22, 2025Jan 17, 2026Mar 13, 2026May 8, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.05
94.9
2025.06
93.7
2026.05
89.7
2026.05
88.5
2026.05
84.5
2026.05
75.6
2026.05
72.6
2026.05
72.1
2026.05
70.6
2026.05
66.1
2025.10
54.2
2025.06
54
2025.10
53.7
2025.10
53.3
2025.06
51.7
2025.10
46.8
2025.10
45.2
2025.10
39.6
2025.06
39.6
2025.06
39
2025.10
37.2
2025.06
33
2025.06
23.9
2025.06
22.2
2025.06
21.7
2025.06
10.6