Compare AI models

Specifications
Parameters
236B—
Context window
128k128k
Benchmarks
HumanEval
84.76%75.7%
MATH
71.02%57.9%
Overview
CompanyDeepSeekZ.ai
Release dateJun 28 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads GLM-4-Air on 2 of the 2 benchmarks they both report (HumanEval, MATH). GLM-4-Air shipped 23 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V2-0628) vs 128k (GLM-4-Air). DeepSeek V2-0628 is open weight, while GLM-4-Air is closed.

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs GLM-4-Air at 75.7%. On MATH, DeepSeek V2-0628 leads at 71.02% vs GLM-4-Air at 57.9%.