Compare AI models

Specifications
Parameters
16B/236B7B
Context window
128k64k
Benchmarks
HumanEval
90.2%83.5%
Overview
CompanyDeepSeekQwen
Release dateJun 14 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 59 days before DeepSeek Coder V2, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2 has 16B/236B parameters, while CodeQwen1.5 has 7B. Context windows are 128k (DeepSeek Coder V2) vs 64k (CodeQwen1.5).

On HumanEval, DeepSeek Coder V2 leads at 90.2% vs CodeQwen1.5 at 83.5%.