Compare AI models

Specifications
Parameters
236B47B
Context window
128k32k
Benchmarks
HumanEval
84.76%40.2%
Overview
CompanyDeepSeekMistral
Release dateJun 28 2024Dec 8 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Mixtral 8×7B on 1 of the 1 benchmark they both report (HumanEval). Mixtral 8×7B shipped 203 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Mixtral 8×7B has 47B. Context windows are 128k (DeepSeek V2-0628) vs 32k (Mixtral 8×7B).

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Mixtral 8×7B at 40.2%.