Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

JailbreakBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Jailbreak AttackJailbreakBench
ASR@100
132
Jailbreak AttackJailbreakBench
ASR96.33
54
Jailbreak AttackJailbreakBench (JBB)
ASR0
54
Adversarial and Jailbreaking Attack DetectionJailbreakBench
AUROC0.8622
20
Red-teaming Attack Success RateJailbreakBench (test)
ASR (Vicuna)82
18
Safety EvaluationJailbreakBench
Reject Rate99
13
Jailbreak DefenseJailbreakBench Qwen-2.5-7B
ASR0
12
Jailbreak DefenseJailbreakBench (JBB)
FNR36.11
12
Jailbreak DetectionJailBreakBench Single Turn 35
F1 Score98
10
Jailbreak AttackJailbreakBench
Safe2Harm ASR (Answer)97.98
10
Jailbreak AttackJailbreakBench GCG
ASR0.58
10
Jailbreak AttackJailbreakBench PAIR
Attack Success Rate (ASR)82
10
Jailbreak AttackJailbreakBench (test)
ASR (Refusal)32
10
Jailbreak DefenseJailbreakBench Vicuna-13B
ASR0
7
Jailbreak DefenseJailbreakBench LLaMA-3-8B
ASR0
7
JailbreakingJailbreakBench
Jailbroken Behaviors (k)1
5
Jailbreak Defense Efficiency and EffectivenessJailbreakBench Summary Aggregates
Avg ASR1
5
Jailbreak AttackJailbreakBench 2024a
Average Latency (s)2.4
4
Showing 18 of 18 rows