Compare AI models

Specifications
Parameters
7B/13B/34B22B
Context window
16k32k
These models have no shared benchmark scores.
Overview
CompanyMetaMistral
Release dateAug 24 2023Sep 17 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Code Llama and Mistral Small 2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama shipped 390 days before Mistral Small 2, so benchmark comparisons should account for the intervening progress.

Code Llama has 7B/13B/34B parameters, while Mistral Small 2 has 22B. Context windows are 16k (Code Llama) vs 32k (Mistral Small 2).

Direct benchmark comparisons are unavailable — Code Llama and Mistral Small 2 don't publish scores on any of the same benchmarks.