Compare AI models

Specifications
Parameters
236B7B
Context window
128k64k
Benchmarks
HumanEval
89%83.5%
Overview
CompanyDeepSeekQwen
Release dateSep 5 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2.5 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 142 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.

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

On HumanEval, DeepSeek V2.5 leads at 89% vs CodeQwen1.5 at 83.5%.