Compare AI models

Specifications
Context window
128k128k
Benchmarks
MMLU-Pro
76.8%75.5%
Overview
CompanyMistralSpaceXSI
Release dateAug 12 2025Aug 13 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3.1 leads Grok‑2 on 1 of the 1 benchmark they both report (MMLU-Pro). Grok‑2 shipped 364 days before Mistral Medium 3.1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3.1) vs 128k (Grok‑2).

On MMLU-Pro, Mistral Medium 3.1 leads at 76.8% vs Grok‑2 at 75.5%.