Compare AI models

Specifications
Parameters
—671B
Context window
200k128k
API pricing
Cheapest input
—$0.256DeepInfra
Cheapest output
—$0.712DeepInfra
—$103StreamLake
Benchmarks
SWE-Bench Verified
62.3%42%
GPQA Diamond
78.2%59.1%
Overview
CompanyAnthropicDeepSeek
Release dateFeb 24 2025Dec 26 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.7 Sonnet leads DeepSeek V3 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek V3 shipped 60 days before Claude 3.7 Sonnet, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.7 Sonnet) vs 128k (DeepSeek V3). Claude 3.7 Sonnet is closed, while DeepSeek V3 is open weight.

On SWE-Bench Verified, Claude 3.7 Sonnet leads at 62.3% vs DeepSeek V3 at 42%. On GPQA Diamond, Claude 3.7 Sonnet leads at 78.2% vs DeepSeek V3 at 59.1%.