Compare AI models

Specifications
Context window
128k—
Benchmarks
HumanEval
92.4%72%
MMLU
85.2%81.5%
Overview
CompanyOpenAIZ.ai
Release dateSep 12 2024Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

o1-mini leads GLM-4 on 2 of the 2 benchmarks they both report (HumanEval, MMLU). GLM-4 shipped 240 days before o1-mini, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On HumanEval, o1-mini leads at 92.4% vs GLM-4 at 72%. On MMLU, o1-mini leads at 85.2% vs GLM-4 at 81.5%.