Compare AI models

Specifications
Context window
200k—
Benchmarks
HumanEval
96.3%72%
MMLU
85.9%81.5%
Overview
CompanyOpenAIZ.ai
Release dateJan 31 2025Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

o3-mini leads GLM-4 on 2 of the 2 benchmarks they both report (HumanEval, MMLU). GLM-4 shipped 381 days before o3-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, o3-mini leads at 96.3% vs GLM-4 at 72%. On MMLU, o3-mini leads at 85.9% vs GLM-4 at 81.5%.