Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-class Classification on Content Rating Descriptors (CRD-9)
Loading...
83.94
Mild Precision
Gemini-2.5-Flash
48.1224
57.4212
66.72
76.0188
May 20, 2026
Mild Precision
Mild Recall
Strong Precision
Strong Recall
Updated 13d ago
Evaluation Results
Method
Method
Links
Mild Precision
Mild Recall
Strong Precision
Strong Recall
Gemini-2.5-Flash
2026.05
83.94
20.91
30.04
49.05
Qwen3-VL-8B
2026.05
73.98
4.58
40.74
45.91
QwenSafe
2026.05
49.5
34.03
27.31
55.25
Feedback
Search any
task
Search any
task