Compare AI models

Specifications
Parameters
236B7B
Context window
128k32k
Benchmarks
HumanEval
81.1%38.4%
MATH
53.9%13.2%
Overview
CompanyDeepSeekMistral
Release dateMay 6 2024May 22 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2 leads Mistral 7B v0.3 on 2 of the 2 benchmarks they both report (HumanEval, MATH). DeepSeek V2 shipped 16 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 has 236B parameters, while Mistral 7B v0.3 has 7B. Context windows are 128k (DeepSeek V2) vs 32k (Mistral 7B v0.3).

On HumanEval, DeepSeek V2 leads at 81.1% vs Mistral 7B v0.3 at 38.4%. On MATH, DeepSeek V2 leads at 53.9% vs Mistral 7B v0.3 at 13.2%.