Compare AI models

Specifications
Parameters
—6B
Context window
128k8k
Benchmarks
HumanEval
74.1%58.5%
MATH
50.6%25.7%
MMLU
81.3%61.4%
GSM8K
90%72.3%
Overview
CompanySpaceXSIZ.ai
Release dateMar 28 2024Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑1.5 leads ChatGLM3-6B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). ChatGLM3-6B shipped 153 days before Grok‑1.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Grok‑1.5) vs 8k (ChatGLM3-6B). Grok‑1.5 is closed, while ChatGLM3-6B is open weight.

On HumanEval, Grok‑1.5 leads at 74.1% vs ChatGLM3-6B at 58.5%. On MATH, Grok‑1.5 leads at 50.6% vs ChatGLM3-6B at 25.7%. On MMLU, Grok‑1.5 leads at 81.3% vs ChatGLM3-6B at 61.4%. On GSM8K, Grok‑1.5 leads at 90% vs ChatGLM3-6B at 72.3%.