Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on WGT
Loading...
90.17
Accuracy
AISA
60.062
67.8785
75.695
83.5115
Feb 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
AISA
Backbone=Llama2-13b-I
2026.02
90.17
gpt-5-mini
Version=2025-08-07
2026.02
89.17
AISA
Backbone=Llama3.1-8b-I
2026.02
89.11
AISA
Backbone=Mistral-7b-I
2026.02
87.92
AISA
Backbone=Qwen3-8b-I
2026.02
87.8
gpt-4o-mini
Version=2024-07-18
2026.02
87.51
gpt-4.1-mini
Version=2025-04-14
2026.02
86.44
AISA
Backbone=GPT-OSS-20b-I
2026.02
85.2
Jailbreak-Classifier
2026.02
84.78
GradSafe
2026.02
83.36
NemoGuard-JailbreakDetect
2026.02
79.22
SPDetector
2026.02
61.57
Llama-Prompt-Guard-2
Parameters=86M
2026.02
61.22
Feedback
Search any
task
Search any
task