List your company

Mathematical Reasoning on Math-500 (pass@1, pass@5)

75.74Pass@1DeepSeek-R1-Qwen-1.5B
9.07626.38343.6960.997Jun 29, 2026

Evaluation results

MethodLinks
DeepSeek-R1-Qwen-1.5BGroup Size (G)=162026.0675.7489.6
DeepSeek-R1-Qwen-1.5BGroup Size (G)=42026.0673.1888.7
DeepSeek-R1-Qwen-1.5BGroup Size (G)=Base2026.0670.885.2
DeepSeek-7BGroup Size (G)=162026.0616.1233.5
DeepSeek-7BGroup Size (G)=42026.0615.4833.3
DeepSeek-7BGroup Size (G)=Base2026.061532.4
Nemotron-4BGroup Size (G)=162026.0613.3431.5
Nemotron-4BGroup Size (G)=42026.0612.6231.6
Nemotron-4BGroup Size (G)=Base2026.0611.6431.4