Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Policy Evaluation on PolicyBench Level 3 CN

80.34Accuracy

QwQ 32B

68.06871.25474.4477.626Apr 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
80.34
2026.04
79.49
2026.04
76.18
2026.04
73.82
2026.04
73.8
73.78
2026.04
72.83
72.33
71.51
2026.04
70.24
2026.04
68.54