Compare AI models

Specifications
Parameters
—6B
Context window
—2k
Benchmarks
HumanEval
85.7%0%
MATH
73%3.1%
MMLU
86.2%25.2%
Overview
CompanySpaceXSIZ.ai
Release dateAug 13 2024Mar 14 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads ChatGLM-6B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). ChatGLM-6B shipped 518 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

Grok‑2 mini is closed, while ChatGLM-6B is open weight.

On HumanEval, Grok‑2 mini leads at 85.7% vs ChatGLM-6B at 0%. On MATH, Grok‑2 mini leads at 73% vs ChatGLM-6B at 3.1%. On MMLU, Grok‑2 mini leads at 86.2% vs ChatGLM-6B at 25.2%.