Compare AI models

Specifications
Parameters
1.3B/5.7B/6.7B/33B—
Context window
16k—
Benchmarks
HumanEval
79.3%72%
Overview
CompanyDeepSeekZ.ai
Release dateNov 2 2023Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder leads GLM-4 on 1 of the 1 benchmark they both report (HumanEval). DeepSeek Coder shipped 75 days before GLM-4, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder is open weight, while GLM-4 is closed.

On HumanEval, DeepSeek Coder leads at 79.3% vs GLM-4 at 72%.