Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Detection on ToxicChat
Loading...
65
F1 Score
Granite Guardian 3.3
37.96
44.98
52
59.02
Mar 7, 2026
F1 Score
AUC
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
AUC
Granite Guardian 3.3
Model size=8B
2026.03
65
94
Breeze Guard
Inference mode=thinking
2026.03
49
84
Breeze Guard
Inference mode=no-thin...
2026.03
39
77
Feedback
Search any
task
Search any
task