Compare AI models

Specifications
Parameters
236B1.5B/7B/72B
Context window
128k4k
Benchmarks
MATH
71.02%84%
Overview
CompanyDeepSeekQwen
Release dateJun 28 2024Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads DeepSeek V2-0628 on 1 of the 1 benchmark they both report (MATH). DeepSeek V2-0628 shipped 41 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Qwen2-Math has 1.5B/7B/72B. Context windows are 128k (DeepSeek V2-0628) vs 4k (Qwen2-Math).

On MATH, Qwen2-Math leads at 84% vs DeepSeek V2-0628 at 71.02%.