Compare AI models

Specifications
Context window
128k—
Benchmarks
HumanEval
74.1%72%
MATH
50.6%47.9%
MMLU
81.3%81.5%
GSM8K
90%87.6%
Overview
CompanySpaceXSIZ.ai
Release dateMar 28 2024Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Grok‑1.5 leads GLM-4 on 3 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). GLM-4 shipped 72 days before Grok‑1.5, 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‑1.5 leads at 74.1% vs GLM-4 at 72%. On MATH, Grok‑1.5 leads at 50.6% vs GLM-4 at 47.9%. On MMLU, GLM-4 leads at 81.5% vs Grok‑1.5 at 81.3%. On GSM8K, Grok‑1.5 leads at 90% vs GLM-4 at 87.6%.