Compare AI models

Specifications
Parameters
7B/67B7B
Context window
4k64k
Benchmarks
HumanEval
73.8%83.5%
Overview
CompanyDeepSeekQwen
Release dateNov 29 2023Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads DeepSeek-LLM on 1 of the 1 benchmark they both report (HumanEval). DeepSeek-LLM shipped 139 days before CodeQwen1.5, so benchmark comparisons should account for the intervening progress.

DeepSeek-LLM has 7B/67B parameters, while CodeQwen1.5 has 7B. Context windows are 4k (DeepSeek-LLM) vs 64k (CodeQwen1.5).

On HumanEval, CodeQwen1.5 leads at 83.5% vs DeepSeek-LLM at 73.8%.