Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on AEG2
Loading...
79.94
Accuracy
gpt-5-mini
41.564
51.527
61.49
71.453
Feb 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
gpt-5-mini
Version=2025-08-07
2026.02
79.94
gpt-4.1-mini
Version=2025-04-14
2026.02
78.85
gpt-4o-mini
Version=2024-07-18
2026.02
78.22
GradSafe
2026.02
78.17
AISA
Backbone=Llama2-13b-I
2026.02
75.26
AISA
Backbone=Qwen3-8b-I
2026.02
72.45
AISA
Backbone=Llama3.1-8b-I
2026.02
72.19
AISA
Backbone=Mistral-7b-I
2026.02
71.67
AISA
Backbone=GPT-OSS-20b-I
2026.02
69.75
SPDetector
2026.02
61.17
Jailbreak-Classifier
2026.02
59.25
NemoGuard-JailbreakDetect
2026.02
58.89
Llama-Prompt-Guard-2
Parameters=86M
2026.02
43.04
Feedback
Search any
task
Search any
task