Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on ADVB
Loading...
100
Accuracy
gpt-4.1-mini
46.0032
60.0216
74.04
88.0584
Feb 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
gpt-4.1-mini
Version=2025-04-14
2026.02
100
gpt-5-mini
Version=2025-08-07
2026.02
100
gpt-4o-mini
Version=2024-07-18
2026.02
99.81
AISA
Backbone=Mistral-7b-I
2026.02
99.81
AISA
Backbone=Llama3.1-8b-I
2026.02
99.81
AISA
Backbone=Llama2-13b-I
2026.02
99.81
AISA
Backbone=Qwen3-8b-I
2026.02
99.81
Jailbreak-Classifier
2026.02
99.62
GradSafe
2026.02
99.23
AISA
Backbone=GPT-OSS-20b-I
2026.02
99.04
NemoGuard-JailbreakDetect
2026.02
97.12
SPDetector
2026.02
74.23
Llama-Prompt-Guard-2
Parameters=86M
2026.02
48.08
Feedback
Search any
task
Search any
task