Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Evaluation on StrongReject
Loading...
95.5
ASR-J
τ_trigger ⊕ PAP
13.756
34.978
56.2
77.422
Apr 10, 2026
ASR-J
ASR-H
ASR-S
Updated 5d ago
Evaluation Results
Method
Method
Links
ASR-J
ASR-H
ASR-S
τ_trigger ⊕ PAP
Model=Backdoor Model (...
2026.04
95.5
83.7
74.5
τ_trigger ⊕ TAP
Model=Backdoor Model (...
2026.04
91.7
81.7
60.4
τ_trigger ⊕ PAIR
Model=Backdoor Model (...
2026.04
88.1
82.1
59.2
PAP
Model=Qwen2.5-7B-Instr...
2026.04
84.2
77
64.8
τ_trigger ⊕ Direct
Model=Backdoor Model (...
2026.04
72
49.2
39.5
TAP
Model=Qwen2.5-7B-Instr...
2026.04
66.5
62.6
51.4
PAIR
Model=Qwen2.5-7B-Instr...
2026.04
61.9
59
49.7
τ_trigger ⊕ Direct
Model=Qwen2.5-7B-Instr...
2026.04
21.4
13.7
8.8
Direct
Model=Qwen2.5-7B-Instr...
2026.04
16.9
11.5
9.2
Feedback
Search any
task
Search any
task