Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Content Moderation on AIR-Bench Text Only (test)
Loading...
94
Precision
ShieldLM-6B-chatglm
53.44
63.97
74.5
85.03
Dec 2, 2025
Precision
Recall
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
ShieldLM-6B-chatglm
Parameters=6B, Backbon...
2025.12
94
68
79
Aetheria
2025.12
92
91
92
ShieldGemma-9B
Parameters=9B
2025.12
88
93
90
OpenAI Moderation
Type=API
2025.12
87
46
60
ShieldGemma-2B
Parameters=2B
2025.12
85
89
87
Azure Content Safety
Type=API
2025.12
85
40
55
Vicuna-7B
Parameters=7B
2025.12
80
92
85
llama-1B-guard
Parameters=1B
2025.12
55
96
70
Feedback
Search any
task
Search any
task