List your company

Policy Evaluation on PolicyBench Level 3 US

77Accuracyo4-mini
65.986468.845771.70574.5643Apr 14, 2026

Evaluation results

MethodLinks
o4-mini2026.0477
Deepseek R12026.0474.6
QwQ 32B2026.0469.9
Gemini 2.5Model Variant=Gemini-2.5-Flash2026.0469.44
Deepseek V32026.0469.39
Claude 3.5Model Variant=Claude-3.5-Sonnet2026.0468.47
Gemma 3-27B2026.0468.37
Claude 3.7Model Variant=Claude-3.7-Sonnet2026.0468.28
GPT-4o2026.0468.13
Gemini 2.0Model Variant=Gemini-2.0-Flash2026.0466.55
LLaMA 42026.0466.41