Compare AI models

Specifications
Context window
128k—
Benchmarks
HumanEval
88.4%72%
MATH
76.1%47.9%
MMLU
87.5%81.5%
Overview
CompanySpaceXSIZ.ai
Release dateAug 13 2024Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 leads GLM-4 on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). GLM-4 shipped 210 days before Grok‑2, 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 leads at 88.4% vs GLM-4 at 72%. On MATH, Grok‑2 leads at 76.1% vs GLM-4 at 47.9%. On MMLU, Grok‑2 leads at 87.5% vs GLM-4 at 81.5%.