List your company

Policy Evaluation on PolicyBench Level 2 (CN)

62.92AccuracyDeepseek R1
55.213657.214359.21561.2157Apr 14, 2026

Evaluation results

MethodLinks
Deepseek R12026.0462.92
Gemini 2.5Model Variant=Gemini-2.5-Flash2026.0460.57
Claude 3.7Model Variant=Claude-3.7-Sonnet2026.0460.47
QwQ 32B2026.0459.79
Claude 3.5Model Variant=Claude-3.5-Sonnet2026.0459.74
LLaMA 42026.0456.56
Gemini 2.0Model Variant=Gemini-2.0-Flash2026.0456.39
GPT-4o2026.0456.34
o4-mini2026.0455.81
Gemma 3-27B2026.0455.56
Deepseek V32026.0455.51