Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Content Moderation on AIR-Bench Text + Image (test)
Loading...
83
Precision
Aetheria
42.44
52.97
63.5
74.03
Dec 2, 2025
Precision
Recall
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
Aetheria
2025.12
83
85
84
OpenAI Moderation
Type=API
2025.12
81
67
73
Azure Content Safety
Type=API
2025.12
72
46
50
Vicuna-7B
Parameters=7B
2025.12
67
56
61
ShieldGemma-9B
Parameters=9B
2025.12
66
84
74
ShieldGemma-2B
Parameters=2B
2025.12
66
88
75
llama-1B-guard
Parameters=1B
2025.12
48
88
62
ShieldLM-6B-chatglm
Parameters=6B, Backbon...
2025.12
44
99
61
Feedback
Search any
task
Search any
task