Compare AI models

Specifications
Parameters
1.3B/5.7B/6.7B/33B7B
Context window
16k32k
Benchmarks
HumanEval
79.3%38.4%
Overview
CompanyDeepSeekMistral
Release dateNov 2 2023May 22 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (HumanEval). DeepSeek Coder shipped 202 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder has 1.3B/5.7B/6.7B/33B parameters, while Mistral 7B v0.3 has 7B. Context windows are 16k (DeepSeek Coder) vs 32k (Mistral 7B v0.3).

On HumanEval, DeepSeek Coder leads at 79.3% vs Mistral 7B v0.3 at 38.4%.