Compare AI models

Specifications
Parameters
—9B
Context window
—128k
Benchmarks
HumanEval
85.7%71.8%
MATH
73%50.6%
MMLU
86.2%72.4%
Overview
CompanySpaceXSIZ.ai
Release dateAug 13 2024Jun 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads GLM-4-9B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). GLM-4-9B shipped 69 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

Grok‑2 mini is closed, while GLM-4-9B is open weight.

On HumanEval, Grok‑2 mini leads at 85.7% vs GLM-4-9B at 71.8%. On MATH, Grok‑2 mini leads at 73% vs GLM-4-9B at 50.6%. On MMLU, Grok‑2 mini leads at 86.2% vs GLM-4-9B at 72.4%.