Compare AI models

Specifications
Parameters
—236B
Context window
100k128k
Benchmarks
HumanEval
58.7%87.2%
Overview
CompanyAnthropicDeepSeek
Release dateAug 9 2023Jul 24 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Claude Instant 1.2 on 1 of the 1 benchmark they both report (HumanEval). Claude Instant 1.2 shipped 350 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude Instant 1.2) vs 128k (DeepSeek Coder V2-0724). Claude Instant 1.2 is closed, while DeepSeek Coder V2-0724 is open weight.

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Claude Instant 1.2 at 58.7%.