Compare AI models

Specifications
Parameters
22B—
Context window
32k—
Benchmarks
HumanEval
81.1%85.7%
Overview
CompanyMistralSpaceXSI
Release dateMay 29 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads Codestral 22B on 1 of the 1 benchmark they both report (HumanEval). Codestral 22B shipped 76 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

Codestral 22B is open weight, while Grok‑2 mini is closed.

On HumanEval, Grok‑2 mini leads at 85.7% vs Codestral 22B at 81.1%.