List your company

Policy Evaluation on PolicyBench Level 1 (CN)

62.02AccuracyDeepseek R1
40.939246.412151.88557.3579Apr 14, 2026

Evaluation results

MethodLinks
Deepseek R12026.0462.02
QwQ 32B2026.0455.87
Claude 3.7Model Variant=Claude-3.7-Sonnet2026.0455.29
Gemini 2.5Model Variant=Gemini-2.5-Flash2026.0454.06
Claude 3.5Model Variant=Claude-3.5-Sonnet2026.0453.77
LLaMA 42026.0449.81
Deepseek V32026.0448.61
Gemini 2.0Model Variant=Gemini-2.0-Flash2026.0447.87
GPT-4o2026.0446.01
o4-mini2026.0445.93
Gemma 3-27B2026.0441.75