Compare AI models

Specifications
Parameters
—6B
Context window
128k8k
Benchmarks
HumanEval
88.4%58.5%
MATH
76.1%25.7%
MMLU
87.5%61.4%
Overview
CompanySpaceXSIZ.ai
Release dateAug 13 2024Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑2 leads ChatGLM3-6B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). ChatGLM3-6B shipped 291 days before Grok‑2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Grok‑2) vs 8k (ChatGLM3-6B). Grok‑2 is closed, while ChatGLM3-6B is open weight.

On HumanEval, Grok‑2 leads at 88.4% vs ChatGLM3-6B at 58.5%. On MATH, Grok‑2 leads at 76.1% vs ChatGLM3-6B at 25.7%. On MMLU, Grok‑2 leads at 87.5% vs ChatGLM3-6B at 61.4%.