Compare AI models

Specifications
Parameters
—236B
Context window
100k128k
Benchmarks
HumanEval
71.2%84.76%
Overview
CompanyAnthropicDeepSeek
Release dateJul 11 2023Jun 28 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Claude 2 on 1 of the 1 benchmark they both report (HumanEval). Claude 2 shipped 353 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude 2) vs 128k (DeepSeek V2-0628). Claude 2 is closed, while DeepSeek V2-0628 is open weight.

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Claude 2 at 71.2%.