Compare AI models

Specifications
Context window
—128k
Benchmarks
HumanEval
85.7%75.7%
MATH
73%57.9%
MMLU
86.2%81.9%
Overview
CompanySpaceXSIZ.ai
Release dateAug 13 2024Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads GLM-4-Air on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). GLM-4-Air shipped 69 days before Grok‑2 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, Grok‑2 mini leads at 85.7% vs GLM-4-Air at 75.7%. On MATH, Grok‑2 mini leads at 73% vs GLM-4-Air at 57.9%. On MMLU, Grok‑2 mini leads at 86.2% vs GLM-4-Air at 81.9%.