Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on ALL-4
Loading...
92.6
Accuracy
gpt-5-mini
52.9032
63.2091
73.515
83.8209
Feb 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
gpt-5-mini
Version=2025-08-07
2026.02
92.6
AISA
Backbone=Llama3.1-8b-I
2026.02
88.89
AISA
Backbone=Llama2-13b-I
2026.02
87.36
gpt-4o-mini
Version=2024-07-18
2026.02
85.89
AISA
Backbone=Qwen3-8b-I
2026.02
85.82
Jailbreak-Classifier
2026.02
85
AISA
Backbone=GPT-OSS-20b-I
2026.02
83.95
AISA
Backbone=Mistral-7b-I
2026.02
82.65
gpt-4.1-mini
Version=2025-04-14
2026.02
81.05
NemoGuard-JailbreakDetect
2026.02
72.9
GradSafe
2026.02
69.8
SPDetector
2026.02
54.64
Llama-Prompt-Guard-2
Parameters=86M
2026.02
54.43
Feedback
Search any
task
Search any
task