Compare AI models

Specifications
Parameters
236B—
Context window
128k128k
Benchmarks
HumanEval
89%75.7%
Overview
CompanyDeepSeekZ.ai
Release dateSep 5 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V2.5 leads GLM-4-Air on 1 of the 1 benchmark they both report (HumanEval). GLM-4-Air shipped 92 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V2.5) vs 128k (GLM-4-Air). DeepSeek V2.5 is open weight, while GLM-4-Air is closed.

On HumanEval, DeepSeek V2.5 leads at 89% vs GLM-4-Air at 75.7%.