List your company

Jailbreak Safety Evaluation on JailbreakBench

2Attack Success Rate (J)Direct
-1.5222.244669.76Apr 10, 2026

Evaluation results

MethodLinks
DirectModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.042—136.4
τ_trigger ⊕ DirectModel=Qwen2.5-7B-Instruct, Backdoor Trigger=τ_trigger2026.0418—108.8
PAIRModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.0449—5233.6
TAPModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.0454—59.238.7
τ_trigger ⊕ DirectModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.0459—4930.5
PAPModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.0476—7153.1
τ_trigger ⊕ TAPModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.0487.5—9158.4
τ_trigger ⊕ PAIRModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.0489—9058.1
τ_trigger ⊕ PAPModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.0490—8256.8
QwQ-32BSetup=Original2026.03—23——
R1-32BSetup=Original2026.03—27——
SafeReActBackbone=QwQ-32B2026.03—2——
SafeReActBackbone=R1-32B2026.03—3——