Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
Benchmarks
MMLU
90.8%81.9%
Overview
CompanyDeepSeekZ.ai
Release dateJan 20 2025Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads GLM-4-Air on 1 of the 1 benchmark they both report (MMLU). GLM-4-Air shipped 229 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 128k (GLM-4-Air). DeepSeek R1 is open weight, while GLM-4-Air is closed.

On MMLU, DeepSeek R1 leads at 90.8% vs GLM-4-Air at 81.9%.