Compare AI models

Specifications
Parameters
7B—
Context window
4k—
Benchmarks
MATH
51.7%47.9%
GSM8K
88.2%87.6%
Overview
CompanyDeepSeekZ.ai
Release dateFeb 5 2024Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-Math leads GLM-4 on 2 of the 2 benchmarks they both report (MATH, GSM8K). GLM-4 shipped 20 days before DeepSeek-Math, so benchmark comparisons should account for the intervening progress.

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

On MATH, DeepSeek-Math leads at 51.7% vs GLM-4 at 47.9%. On GSM8K, DeepSeek-Math leads at 88.2% vs GLM-4 at 87.6%.