List your company

Mathematical Reasoning on Hendrycks-MATH (held-out 1,000-question)

71.7Accuracy (Base)R1-Distill-1.5B
27.08438.66750.2561.833Oct 8, 2025

Evaluation results

MethodLinks
R1-Distill-1.5BBase Model=Qwen2.5-Math-1.5B2025.1071.769.894.1-8.5
R1-Distill-14BBase Model=Qwen2.5-14B2025.1067.772.297.115.4
ORZ-7BBase Model=Qwen2.5-7B2025.1066.977.78949.1
R1-Distill-32BBase Model=Qwen2.5-32B2025.1065.769.797.512.5
ORZ-32BBase Model=Qwen2.5-32B2025.1065.780.695.949.2
QwQ-32BBase Model=Qwen2.5-32B2025.1065.670.99816.3
ORZ-1.5BBase Model=Qwen2.5-1.5B2025.103960.363.188.3
R1-Distill-8BBase Model=Llama-3.1-8B2025.1030.226.695.8-5.5
ORZ-0.5BBase Model=Qwen2.5-0.5B2025.1028.839.238.5107.4