Compare AI models

Specifications
Parameters
7B/13B/34B—
Context window
16k128k
These models have no shared benchmark scores.
Overview
CompanyMetaMistral
Release dateAug 24 2023Sep 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Code Llama and Magistral Medium 1.2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama shipped 755 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 16k (Code Llama) vs 128k (Magistral Medium 1.2). Code Llama is open weight, while Magistral Medium 1.2 is closed.

Direct benchmark comparisons are unavailable — Code Llama and Magistral Medium 1.2 don't publish scores on any of the same benchmarks.