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

Over Refusal on Over Refusal scenario

100ASR

HQQ

-3.79223.15450.177.046May 14, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.05
100--
2026.05
99.9--
2026.05
99.5--
2026.05
98.3--
2026.05
95.8--
2026.05
95--
2026.05
94.3--
2026.05
93.4--
2026.05
92.9--
2026.05
92.9--
2026.05
89.6--
2026.05
89.1--
2026.05
85.1--
2026.05
84.4--
2026.05
81.9--
2026.05
78.3--
2026.05
74.3--
2026.05
73.7--
2026.05
70.4--
2026.05
68.8--
2026.05
66.9--
2026.05
49.6--
2026.05
48.7--
2026.05
48.3--
2026.05
47.7--
2026.05
43--
2026.05
41.7--
2026.05
37.9--
2026.05
33.7--
2026.05
27.7--
2026.05
25.1--
2026.05
13.5--
2026.05
10.6--
2026.05
7.7--
2026.05
5.3--
2026.05
4.3--
2026.05
4.3--
2026.05
1.2--
2026.05
0.8--
2026.05
0.8--
2026.05
0.3--
2026.05
0.2--
2025.10
-1.10.4
2025.10
-93.90.3
2025.10
-51.30.9
2025.10
-40.92.8
2025.10
-67.81.1
2025.10
-93.70.8
2025.10
-96.34.1
2025.10
-98.41.7
2025.10
-0.50.5
2025.10
-95.50.3
2025.10
-70.40.3
2025.10
-21.42.9
2025.10
-78.32.7
2025.10
-930.8
2025.10
-63.21.8
2025.10
-97.32.9
2025.10
-2.12.5
2025.10
-92.72.1
2025.10
-78.82.6
2025.10
-47.98.7
2025.10
-98.74.6
2025.10
-91.12.1
2025.10
-78.76.9
2025.10
-97.24.1