Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Policy Violation Detection on SB+SI
Loading...
69
True Positives
VIGIL
32.6
42.05
51.5
60.95
Jun 25, 2026
True Positives
False Positives
Precision
Recall
F1 Score
Updated 29d ago
Evaluation Results
Method
Method
Links
True Positives
False Positives
Precision
Recall
F1 Score
VIGIL
Tests=152
2026.06
69
8
89.6
95.8
92.6
LLM-as-judge
Tests=152
2026.06
48
5
90.6
66.7
76.8
Progent
Tests=152
2026.06
40
47
46
55.6
50.3
AgentSpec
Tests=152
2026.06
34
12
73.9
47.2
57.6
Feedback
Search any
task
Search any
task