Compare AI models

Specifications
Parameters
—671B
Context window
200k128k
Benchmarks
SWE-Bench Verified
33.4%49.2%
GPQA Diamond
59.4%71.5%
MMLU
90.4%90.8%
Overview
CompanyAnthropicDeepSeek
Release dateJun 20 2024Jan 20 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Claude 3.5 Sonnet on 3 of the 3 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, MMLU). Claude 3.5 Sonnet shipped 214 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Sonnet) vs 128k (DeepSeek R1). Claude 3.5 Sonnet is closed, while DeepSeek R1 is open weight.

On SWE-Bench Verified, DeepSeek R1 leads at 49.2% vs Claude 3.5 Sonnet at 33.4%. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs Claude 3.5 Sonnet at 59.4%. On MMLU, DeepSeek R1 leads at 90.8% vs Claude 3.5 Sonnet at 90.4%.