List your company

Mathematical Reasoning on GSM-Plus 2400

40.25Pass@1DeepSeek-7B
7.864416.272224.6833.0878Jun 29, 2026

Evaluation results

MethodLinks
DeepSeek-7BGroup Size (G)=42026.0640.2560.5
DeepSeek-R1-Qwen-1.5BGroup Size (G)=162026.0636.5257.86
DeepSeek-R1-Qwen-1.5BGroup Size (G)=42026.0634.856.44
DeepSeek-R1-Qwen-1.5BGroup Size (G)=Base2026.0633.4855.54
DeepSeek-7BGroup Size (G)=162026.0630.8352.19
DeepSeek-7BGroup Size (G)=Base2026.0625.6449.25
Nemotron-4BGroup Size (G)=162026.0620.3240.86
Nemotron-4BGroup Size (G)=42026.0619.4642.02
Nemotron-4BGroup Size (G)=Base2026.069.1121.92