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

Jailbreaking on StrongReject (test)

89.8Attack Success Rate (ASR)

PAD

-3.59220.65444.969.146Jun 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
89.8---4.47
2026.06
87.9---4.5
2026.06
87.5---4.55
2026.06
87.2---4.64
2026.06
87---4.68
2026.06
83.5---3.66
2026.06
83.1---4.55
2026.06
83---4.63
2026.06
82.1---4.29
2026.06
81.8---4.42
2026.06
81---4.55
2026.06
81---4.58
2026.06
80.8---4.51
2026.06
79---4.64
2026.06
75.7---4
2026.06
75---4.4
2026.06
74.5---3.41
2026.06
74.3---4.34
2026.06
72.5---3.75
2026.06
72.5---4.15
2026.06
72---3.36
2026.06
62.5---3.18
2026.06
46.5---2.93
2026.06
36---2.54
2026.06
32.9---3.46
2026.06
32.5---2.04
2026.06
31---1.97
2026.06
30.7---2.11
2026.06
26---2.1
2026.06
20.8---3.09
2026.06
15.7---1.63
2026.06
12---1.72
2026.06
10.8---1.57
2026.06
10.5---1.68
2026.06
9.5---1.3
2026.06
8---1.47
2026.06
4---1.2
2026.06
1.6---1.08
2026.06
1.5---1.15
2026.06
0.6---1.04
2026.06
0.3---1.02
2026.06
0---1.02
2026.04
-38.733.417.1-
2026.04
-66.260.413.6-
2026.04
-8889.098-
2026.04
-58.353.111.8-
2026.04
-61.556.410.9-
2026.04
-78.673.29.9-
2026.04
-7165.412.4-
2026.04
-63.658.211.2-
2026.04
-94892.2-
2026.04
-34.730.117.9-
2026.04
-58.853.214.2-
2026.04
-80748.6-
2026.04
-52.647.912.7-
2026.04
-5550.111.6-
2026.04
-7670.410.2-
2026.04
-66.96113-
2026.04
-5650.812-
2026.04
-86802.2-
2026.04
-40.135.116.5-
2026.04
-67.962.313.1-
2026.04
-90867.9-
2026.04
-60.855.911.5-
2026.04
-63.958.810.6-
2026.04
-79.274.69.8-
2026.04
-7266.912.2-
2026.04
-6559.811.1-
2026.04
-96922.1-