Compare AI models

Specifications
Parameters
314B1.5B/4B
Context window
8k8k
Benchmarks
MMLU
73%54.84%
GSM8K
62.9%54.89%
Overview
CompanySpaceXSIZ.ai
Release dateNov 3 2023Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑1 leads GLM-Edge on 2 of the 2 benchmarks they both report (MMLU, GSM8K). Grok‑1 shipped 392 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

Grok‑1 has 314B parameters, while GLM-Edge has 1.5B/4B. Context windows are 8k (Grok‑1) vs 8k (GLM-Edge).

On MMLU, Grok‑1 leads at 73% vs GLM-Edge at 54.84%. On GSM8K, Grok‑1 leads at 62.9% vs GLM-Edge at 54.89%.