Compare AI models

Specifications
Parameters
1.3B/5.7B/6.7B/33B—
Context window
16k128k
Benchmarks
HumanEval
79.3%75.7%
Overview
CompanyDeepSeekZ.ai
Release dateNov 2 2023Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder leads GLM-4-Air on 1 of the 1 benchmark they both report (HumanEval). DeepSeek Coder shipped 216 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 16k (DeepSeek Coder) vs 128k (GLM-4-Air). DeepSeek Coder is open weight, while GLM-4-Air is closed.

On HumanEval, DeepSeek Coder leads at 79.3% vs GLM-4-Air at 75.7%.