Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Injection and Jailbreak Detection on VPI
Loading...
100
Recall
WARD-0.8b
77.224
83.137
89.05
94.963
May 14, 2026
Recall
Updated 19d ago
Evaluation Results
Method
Method
Links
Recall
WARD-0.8b
Model Category=Ours
2026.05
100
GPT-5.4
Model Category=Closed-...
2026.05
84.97
WebAgentGuard-8b
Model Category=Guard m...
2026.05
78.1
Feedback
Search any
task
Search any
task
