Compare AI models

Specifications
Parameters
236B47B
Context window
128k32k
Benchmarks
HumanEval
87.2%40.2%
Overview
CompanyDeepSeekMistral
Release dateJul 24 2024Dec 8 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Mixtral 8×7B on 1 of the 1 benchmark they both report (HumanEval). Mixtral 8×7B shipped 229 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2-0724 has 236B parameters, while Mixtral 8×7B has 47B. Context windows are 128k (DeepSeek Coder V2-0724) vs 32k (Mixtral 8×7B).

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Mixtral 8×7B at 40.2%.