Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on XST
Loading...
95.11
Accuracy
AISA
53.978
64.6565
75.335
86.0135
Feb 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
AISA
Backbone=Llama2-13b-I
2026.02
95.11
AISA
Backbone=Qwen3-8b-I
2026.02
93.78
AISA
Backbone=Mistral-7b-I
2026.02
93.33
AISA
Backbone=Llama3.1-8b-I
2026.02
92.89
gpt-4.1-mini
Version=2025-04-14
2026.02
92.44
gpt-5-mini
Version=2025-08-07
2026.02
90.89
GradSafe
2026.02
90.67
AISA
Backbone=GPT-OSS-20b-I
2026.02
88.89
gpt-4o-mini
Version=2024-07-18
2026.02
85.78
SPDetector
2026.02
70
NemoGuard-JailbreakDetect
2026.02
67.33
Jailbreak-Classifier
2026.02
64.22
Llama-Prompt-Guard-2
Parameters=86M
2026.02
55.56
Feedback
Search any
task
Search any
task