Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multilingual Safety Evaluation on 6 Safety Datasets High-Resource Languages
Loading...
0.8659
Safety Score (Fr)
PG-Qwen-Smol
0.732988
0.767494
0.802
0.836506
Dec 2, 2025
Safety Score (Fr)
Safety Score (It)
Safety Score (De)
Safety Score (Pt)
Safety Score (Es)
Updated 4d ago
Evaluation Results
Method
Method
Links
Safety Score (Fr)
Safety Score (It)
Safety Score (De)
Safety Score (Pt)
Safety Score (Es)
PG-Qwen-Smol
Model Size=0.5B, Multi...
2025.12
0.8659
0.8596
0.8468
0.8528
0.8655
CREST-LARGE
Model Size=0.5B, Multi...
2025.12
0.8606
0.8608
0.8565
0.8533
0.8555
LlamaGuard3
Model Size=8B, Multili...
2025.12
0.8407
0.8396
0.8278
0.8281
0.8345
CREST-BASE
Model Size=0.25B, Mult...
2025.12
0.8342
0.8299
0.8435
0.818
0.8321
Duoguard
Model Size=0.5B, Multi...
2025.12
0.7381
0.6142
0.7686
0.674
0.7413
Feedback
Search any
task
Search any
task