List your company

Mathematical Reasoning on NuminaMath (pass@1, pass@5)

45.96Pass@1DeepSeek-R1-Qwen-1.5B
13.293621.774330.25538.7357Jun 29, 2026

Evaluation results

MethodLinks
DeepSeek-R1-Qwen-1.5BGroup Size (G)=162026.0645.9660.61
DeepSeek-R1-Qwen-1.5BGroup Size (G)=42026.0644.9560.11
DeepSeek-R1-Qwen-1.5BGroup Size (G)=Base2026.0642.4261.62
DeepSeek-7BGroup Size (G)=42026.0617.5735.35
Nemotron-4BGroup Size (G)=162026.0617.3732.32
DeepSeek-7BGroup Size (G)=Base2026.0616.9730.3
DeepSeek-7BGroup Size (G)=162026.0615.9628.79
Nemotron-4BGroup Size (G)=Base2026.0614.5533.33
Nemotron-4BGroup Size (G)=42026.0614.5530.81