Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on FQ-PH
Loading...
86.54
ACC
Jailbreak-Classifier
51.2008
60.3754
69.55
78.7246
Feb 14, 2026
ACC
Updated 4d ago
Evaluation Results
Method
Method
Links
ACC
Jailbreak-Classifier
2026.02
86.54
AISA
Backbone=Llama3.1-8b-I
2026.02
78.85
AISA
Backbone=Qwen3-8b-I
2026.02
78.21
AISA
Backbone=Mistral-7b-I
2026.02
77.56
AISA
Backbone=Llama2-13b-I
2026.02
77.56
NemoGuard-JailbreakDetect
2026.02
76.28
gpt-5-mini
Version=2025-08-07
2026.02
75.64
gpt-4.1-mini
Version=2025-04-14
2026.02
74.36
GradSafe
2026.02
73.72
gpt-4o-mini
Version=2024-07-18
2026.02
72.44
AISA
Backbone=GPT-OSS-20b-I
2026.02
68.59
SPDetector
2026.02
63.46
Llama-Prompt-Guard-2
Parameters=86M
2026.02
52.56
Feedback
Search any
task
Search any
task