List your company

Content Safety on COLD (test)

74.8Macro F1-ScoreGPT-3.5
60.65664.3286871.672Jun 26, 2026

Evaluation results

MethodLinks
GPT-3.52026.0674.8
Qwen2-72BParameters=72B2026.0673.5
Yuvion-32BParameters=32B2026.0672.6
Qwen1.5-72BParameters=72B2026.0671
DeepSeek-67BParameters=67B2026.0670.8
Yuvion-8BParameters=8B2026.0669.6
Qwen2-32BParameters=32B2026.0664.4
Qwen2-8BParameters=8B2026.0661.2