Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Content Moderation on AIR-Bench Image Only (test)
Loading...
94
Precision
ShieldGemma-9B
49.28
60.89
72.5
84.11
Dec 2, 2025
Precision
Recall
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
ShieldGemma-9B
Parameters=9B
2025.12
94
72
82
ShieldGemma-2B
Parameters=2B
2025.12
90
61
73
Aetheria
2025.12
90
85
87
OpenAI Moderation
Type=API
2025.12
74
17
28
Azure Content Safety
Type=API
2025.12
73
15
25
Vicuna-7B
Parameters=7B
2025.12
57
76
65
llama-1B-guard
Parameters=1B
2025.12
53
74
62
ShieldLM-6B-chatglm
Parameters=6B, Backbon...
2025.12
51
97
67
Feedback
Search any
task
Search any
task