Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Content Safety on COLD (test)
Loading...
74.8
Macro F1-Score
GPT-3.5
60.656
64.328
68
71.672
Jun 26, 2026
Macro F1-Score
Updated 26d ago
Evaluation Results
Method
Method
Links
Macro F1-Score
GPT-3.5
2026.06
74.8
Qwen2-72B
Parameters=72B
2026.06
73.5
Yuvion-32B
Parameters=32B
2026.06
72.6
Qwen1.5-72B
Parameters=72B
2026.06
71
DeepSeek-67B
Parameters=67B
2026.06
70.8
Yuvion-8B
Parameters=8B
2026.06
69.6
Qwen2-32B
Parameters=32B
2026.06
64.4
Qwen2-8B
Parameters=8B
2026.06
61.2
Feedback
Search any
task
Search any
task