Compare AI models

Specifications
Parameters
236B22B
Context window
128k32k
Benchmarks
LiveCodeBench
39.7%31.5%
HumanEval
87.2%81.1%
Overview
CompanyDeepSeekMistral
Release dateJul 24 2024May 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Codestral 22B on 2 of the 2 benchmarks they both report (LiveCodeBench, HumanEval). Codestral 22B shipped 56 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2-0724 has 236B parameters, while Codestral 22B has 22B. Context windows are 128k (DeepSeek Coder V2-0724) vs 32k (Codestral 22B).

On LiveCodeBench, DeepSeek Coder V2-0724 leads at 39.7% vs Codestral 22B at 31.5%. On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Codestral 22B at 81.1%.