Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safety Moderation on Harmbench
Loading...
86.4
F1 Score
BingoGuard
78.288
80.394
82.5
84.606
Dec 5, 2025
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
BingoGuard
Parameter Count=8B
2025.12
86.4
WildGuard
Parameter Count=7B
2025.12
86.2
Roblox Guard 1.0
Parameter Count=8B
2025.12
85.7
LlamaGuard3
Parameter Count=8B
2025.12
84.9
ShieldGemma
Parameter Count=7B
2025.12
84.8
GPT-4o
2025.12
83.5
NemoGuard
Parameter Count=8B
2025.12
78.6
Feedback
Search any
task
Search any
task