Compare AI models

Specifications
Context window
256k—
Benchmarks
HumanEval
86.6%85.7%
Overview
CompanyMistralSpaceXSI
Release dateJan 13 2025Aug 13 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Codestral 25.01 leads Grok‑2 mini on 1 of the 1 benchmark they both report (HumanEval). Grok‑2 mini shipped 153 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On HumanEval, Codestral 25.01 leads at 86.6% vs Grok‑2 mini at 85.7%.