Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safety Moderation on Wild Guard Response
Loading...
88.9
F1 Score
WildGuard
9.028
29.764
50.5
71.236
Dec 5, 2025
Dec 7, 2025
Dec 10, 2025
Dec 13, 2025
Dec 16, 2025
Dec 19, 2025
Dec 22, 2025
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
WildGuard
Type=Response
2025.12
88.9
GGuard
Type=Response
2025.12
86
Roblox Guard 1.0
Parameter Count=8B
2025.12
80.6
BingoGuard
Parameter Count=8B
2025.12
80.1
ShieldGemma
Type=Response
2025.12
80
ShieldGemma
Parameter Count=7B
2025.12
77.8
Llama Guard
Type=Response
2025.12
76.8
NemoGuard
Parameter Count=8B
2025.12
75.7
WildGuard
Parameter Count=7B
2025.12
75.4
GPT-4o
2025.12
73.1
LlamaGuard3
Parameter Count=8B
2025.12
70.2
OAI Moderator
Type=Response
2025.12
12.1
Feedback
Search any
task
Search any
task