Compare AI models

Specifications
Context window
200k128k
Benchmarks
HumanEval
99.3%75.7%
MMLU
90.3%81.9%
Overview
CompanyOpenAIZ.ai
Release dateApr 16 2025Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

o4-mini-high leads GLM-4-Air on 2 of the 2 benchmarks they both report (HumanEval, MMLU). GLM-4-Air shipped 315 days before o4-mini-high, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (o4-mini-high) vs 128k (GLM-4-Air).

On HumanEval, o4-mini-high leads at 99.3% vs GLM-4-Air at 75.7%. On MMLU, o4-mini-high leads at 90.3% vs GLM-4-Air at 81.9%.