Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Moderation on Public Safety Benchmark Suite Average (EN)
Loading...
86
F1 Score
Wildguard
67.28
72.14
77
81.86
Mar 17, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Wildguard
Size=7B
2026.03
86
MD-Judge
Size=7B
2026.03
85
FanarGuard
Size=4B
2026.03
83
Llama-Guard-3
Size=8B
2026.03
81
PolyGuard-Ministral
Size=8B
2026.03
79
PolyGuard-Qwen
Size=7B
2026.03
78
PolyGuard-Smol
Size=0.5B
2026.03
73
ShieldGemma-2b
Size=2B
2026.03
68
Feedback
Search any
task
Search any
task