Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
OOD safety category inference (Stage 2) on OpenAI Moderation
Loading...
36.45
Mean Reward
Gemini2.5-Flash
7.7668
15.2134
22.66
30.1066
Dec 29, 2025
Mean Reward
Updated 3d ago
Evaluation Results
Method
Method
Links
Mean Reward
Gemini2.5-Flash
2025.12
36.45
ProGuard-7B
2025.12
29.05
ProGuard-3B
2025.12
28.31
GPT4o-mini
2025.12
8.87
Feedback
Search any
task
Search any
task