Compare AI models

Specifications
Context window
200k128k
Benchmarks
HumanEval
97.6%75.7%
MMLU
86.9%81.9%
Overview
CompanyOpenAIZ.ai
Release dateJan 31 2025Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

o3-mini-high leads GLM-4-Air on 2 of the 2 benchmarks they both report (HumanEval, MMLU). GLM-4-Air shipped 240 days before o3-mini-high, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (o3-mini-high) vs 128k (GLM-4-Air).

On HumanEval, o3-mini-high leads at 97.6% vs GLM-4-Air at 75.7%. On MMLU, o3-mini-high leads at 86.9% vs GLM-4-Air at 81.9%.