Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on SB
Loading...
98.33
COR
gpt-4o-mini
4.73
29.03
53.33
77.63
Feb 14, 2026
COR
Updated 4d ago
Evaluation Results
Method
Method
Links
COR
gpt-4o-mini
Version=2024-07-18
2026.02
98.33
gpt-4.1-mini
Version=2025-04-14
2026.02
98.33
gpt-5-mini
Version=2025-08-07
2026.02
98.33
AISA
Backbone=Mistral-7b-I
2026.02
96.67
AISA
Backbone=Llama3.1-8b-I
2026.02
96.67
AISA
Backbone=Llama2-13b-I
2026.02
96.67
AISA
Backbone=Qwen3-8b-I
2026.02
95.83
GradSafe
2026.02
95
AISA
Backbone=GPT-OSS-20b-I
2026.02
94.17
Jailbreak-Classifier
2026.02
92.5
NemoGuard-JailbreakDetect
2026.02
79.17
SPDetector
2026.02
76.67
Llama-Prompt-Guard-2
Parameters=86M
2026.02
8.33
Feedback
Search any
task
Search any
task