Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Content Safety on ChineseHarm (test)
Loading...
97.9
Macro F1-Score
Yuvion-32B
52.66
64.405
76.15
87.895
Jun 26, 2026
Macro F1-Score
Updated 26d ago
Evaluation Results
Method
Method
Links
Macro F1-Score
Yuvion-32B
Parameters=32B
2026.06
97.9
Yuvion-8B
Parameters=8B
2026.06
96.8
Qwen2-32B
Parameters=32B
2026.06
93.2
Qwen2-8B
Parameters=8B
2026.06
90.8
Qwen2-72B
Parameters=72B
2026.06
87.9
GPT-3.5
2026.06
85.3
Qwen1.5-72B
Parameters=72B
2026.06
81.2
DeepSeek-67B
Parameters=67B
2026.06
54.4
Feedback
Search any
task
Search any
task