Compare AI models

Specifications
Parameters
236B—
Context window
128k32k
Benchmarks
HumanEval
87.2%45.1%
Overview
CompanyDeepSeekMistral
Release dateJul 24 2024Feb 26 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Mistral Large on 1 of the 1 benchmark they both report (HumanEval). Mistral Large shipped 149 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2-0724) vs 32k (Mistral Large). DeepSeek Coder V2-0724 is open weight, while Mistral Large is closed.

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Mistral Large at 45.1%.