List your company

Mathematical Reasoning on DAPO + MATH

9.6Training Time (hours)DS
8.67214.93621.227.464Mar 26, 2026

Evaluation results

MethodLinks
DSModel backbone=DeepSeek-R1-Distill-Qwen-1.5B, Training steps=1000, Hardware (GPUs)=8x A1002026.039.66.168.784.4
HIVEModel backbone=DeepSeek-R1-Distill-Qwen-1.5B, Training steps=1000, Hardware (GPUs)=8x A1002026.0310.16.742.759.5
GRESOModel backbone=DeepSeek-R1-Distill-Qwen-1.5B, Training steps=1000, Hardware (GPUs)=8x A1002026.0310.46.645.962.9
DSModel backbone=Qwen2.5-Math-1.5B, Training steps=1000, Hardware (GPUs)=8x A1002026.0310.9677.394.2
HIVEModel backbone=Qwen2.5-Math-1.5B, Training steps=1000, Hardware (GPUs)=8x A1002026.0311.26.242.159.5
GRESOModel backbone=Qwen2.5-Math-1.5B, Training steps=1000, Hardware (GPUs)=8x A1002026.0311.36.44663.7
DSModel backbone=Llama3.2-3b-Instruct, Training steps=1000, Hardware (GPUs)=8x A1002026.0320.610.2218.3249.1
GRESOModel backbone=Llama3.2-3b-Instruct, Training steps=1000, Hardware (GPUs)=8x A1002026.0321.810.5116.5148.8
HIVEModel backbone=Llama3.2-3b-Instruct, Training steps=1000, Hardware (GPUs)=8x A1002026.0322.210.690.4123.2
DSModel backbone=Qwen2.5-Math-7B, Training steps=1000, Hardware (GPUs)=8x A1002026.0332.112.6153.7198.4
HIVEModel backbone=Qwen2.5-Math-7B, Training steps=1000, Hardware (GPUs)=8x A1002026.0332.712.940.285.8
GRESOModel backbone=Qwen2.5-Math-7B, Training steps=1000, Hardware (GPUs)=8x A1002026.0332.813.266.3112.3