Compare AI models

Specifications
Parameters
—671B
Context window
200k128k
Benchmarks
SWE-Bench Verified
72.5%49.2%
GPQA Diamond
79.6%71.5%
Overview
CompanyAnthropicDeepSeek
Release dateMay 22 2025Jan 20 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Opus 4 leads DeepSeek R1 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek R1 shipped 122 days before Claude Opus 4, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude Opus 4) vs 128k (DeepSeek R1). Claude Opus 4 is closed, while DeepSeek R1 is open weight.

On SWE-Bench Verified, Claude Opus 4 leads at 72.5% vs DeepSeek R1 at 49.2%. On GPQA Diamond, Claude Opus 4 leads at 79.6% vs DeepSeek R1 at 71.5%.