Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Moderation on OAI Mod
Loading...
82.1
F1 Score
ShieldGemma
69.828
73.014
76.2
79.386
Dec 5, 2025
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
ShieldGemma
Parameter Count=7B
2025.12
82.1
LlamaGuard3
Parameter Count=8B
2025.12
79.4
BingoGuard
Parameter Count=8B
2025.12
77.9
NemoGuard
Parameter Count=8B
2025.12
77
WildGuard
Parameter Count=7B
2025.12
72.1
GPT-4o
2025.12
70.4
Roblox Guard 1.0
Parameter Count=8B
2025.12
70.3
Feedback
Search any
task
Search any
task