Compare AI models

Specifications
Parameters
236B14B
Context window
128k2k
Benchmarks
HumanEval
87.2%32.3%
Overview
CompanyDeepSeekQwen
Release dateJul 24 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Qwen-14B on 1 of the 1 benchmark they both report (HumanEval). Qwen-14B shipped 303 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2-0724 has 236B parameters, while Qwen-14B has 14B. Context windows are 128k (DeepSeek Coder V2-0724) vs 2k (Qwen-14B).

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Qwen-14B at 32.3%.