Compare AI models

Specifications
Parameters
—236B
Context window
200k128k
Benchmarks
SWE-Bench Verified
7.2%19%
HumanEval
75.9%87.2%
Overview
CompanyAnthropicDeepSeek
Release dateMar 4 2024Jul 24 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Claude 3 Haiku on 2 of the 2 benchmarks they both report (SWE-Bench Verified, HumanEval). Claude 3 Haiku shipped 142 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Haiku) vs 128k (DeepSeek Coder V2-0724). Claude 3 Haiku is closed, while DeepSeek Coder V2-0724 is open weight.

On SWE-Bench Verified, DeepSeek Coder V2-0724 leads at 19% vs Claude 3 Haiku at 7.2%. On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Claude 3 Haiku at 75.9%.