Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safety on Cultural Kaleidoscope
Loading...
76.6
F1 Score
DuoGuard
24.8808
38.3079
51.735
65.1621
Dec 2, 2025
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
DuoGuard
Scale=Small (<=0.5B)
2025.12
76.6
PG-Qwen
Scale=Large (>=2.5B)
2025.12
75.71
CREST-BASE
Scale=Small (<=0.5B)
2025.12
69.42
Walledguard
Scale=Small (<=0.5B)
2025.12
67.43
CREST-LARGE
Scale=Small (<=0.5B)
2025.12
56.79
PQ-Qwen-Smol
Scale=Small (<=0.5B)
2025.12
55.3
LlamaGuard
Scale=Large (>=2.5B)
2025.12
26.87
Feedback
Search any
task
Search any
task