Compare AI models

Specifications
Parameters
—236B
Context window
100k128k
Benchmarks
HumanEval
58.7%84.76%
Overview
CompanyAnthropicDeepSeek
Release dateAug 9 2023Jun 28 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Claude Instant 1.2 on 1 of the 1 benchmark they both report (HumanEval). Claude Instant 1.2 shipped 324 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude Instant 1.2) vs 128k (DeepSeek V2-0628). Claude Instant 1.2 is closed, while DeepSeek V2-0628 is open weight.

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Claude Instant 1.2 at 58.7%.