Compare AI models

Specifications
Parameters
314B6B
Context window
8k8k
Benchmarks
HumanEval
63.2%58.5%
MATH
23.9%25.7%
MMLU
73%61.4%
GSM8K
62.9%72.3%
Overview
CompanySpaceXSIZ.ai
Release dateNov 3 2023Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑1 and ChatGLM3-6B are evenly matched across the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). ChatGLM3-6B shipped 7 days before Grok‑1, so benchmark comparisons should account for the intervening progress.

Grok‑1 has 314B parameters, while ChatGLM3-6B has 6B. Context windows are 8k (Grok‑1) vs 8k (ChatGLM3-6B).

On HumanEval, Grok‑1 leads at 63.2% vs ChatGLM3-6B at 58.5%. On MATH, ChatGLM3-6B leads at 25.7% vs Grok‑1 at 23.9%. On MMLU, Grok‑1 leads at 73% vs ChatGLM3-6B at 61.4%. On GSM8K, ChatGLM3-6B leads at 72.3% vs Grok‑1 at 62.9%.