Compare AI models

Specifications
Parameters
16B/236B7B
Context window
128k32k
Benchmarks
HumanEval
90.2%38.4%
MATH
75.7%13.2%
Overview
CompanyDeepSeekMistral
Release dateJun 14 2024May 22 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2 leads Mistral 7B v0.3 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Mistral 7B v0.3 shipped 23 days before DeepSeek Coder V2, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2 has 16B/236B parameters, while Mistral 7B v0.3 has 7B. Context windows are 128k (DeepSeek Coder V2) vs 32k (Mistral 7B v0.3).

On HumanEval, DeepSeek Coder V2 leads at 90.2% vs Mistral 7B v0.3 at 38.4%. On MATH, DeepSeek Coder V2 leads at 75.7% vs Mistral 7B v0.3 at 13.2%.