Compare AI models

Specifications
Parameters
314B6B
Context window
8k8k
Benchmarks
HumanEval
63.2%35.9%
Overview
CompanySpaceXSIZ.ai
Release dateNov 3 2023Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑1 leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 101 days before Grok‑1, so benchmark comparisons should account for the intervening progress.

Grok‑1 has 314B parameters, while CodeGeeX2-6B has 6B. Context windows are 8k (Grok‑1) vs 8k (CodeGeeX2-6B).

On HumanEval, Grok‑1 leads at 63.2% vs CodeGeeX2-6B at 35.9%.