Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Content Moderation on Lexica UnsafeBench (test)
Loading...
65
Hate Safety Score
GGuard
23.4
34.2
45
55.8
Dec 22, 2025
Hate Safety Score
Harassment Safety Score
Violence Safety Score
Self-harm Safety Score
Sexual Safety Score
Shocking Safety Score
Illegal Activity Safety Score
Deception Safety Score
Political Safety Score
Health Safety Score
Spam Safety Score
Overall Safety Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Hate Safety Score
Harassment Safety Score
Violence Safety Score
Self-harm Safety Score
Sexual Safety Score
Shocking Safety Score
Illegal Activity Safety Score
Deception Safety Score
Political Safety Score
Health Safety Score
Spam Safety Score
Overall Safety Score
GGuard
2025.12
65
60.6
70.5
69.8
50.6
60.6
65.1
51.1
73.5
61.5
55.9
62
GPT-4V
Evaluation Source=Unsa...
2025.12
25
63.5
71.2
61.3
82.7
87.5
70.1
42.2
90.9
62.1
17.1
70.7
Feedback
Search any
task
Search any
task
