Compare AI models

Specifications
Parameters
—671B
Context window
200k128k
Benchmarks
SWE-Bench Verified
49%49.2%
GPQA Diamond
65%71.5%
MMLU
90.5%90.8%
Overview
CompanyAnthropicDeepSeek
Release dateOct 22 2024Jan 20 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Claude 3.5 Sonnet (upgraded) on 3 of the 3 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, MMLU). Claude 3.5 Sonnet (upgraded) shipped 90 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, DeepSeek R1 leads at 49.2% vs Claude 3.5 Sonnet (upgraded) at 49%. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs Claude 3.5 Sonnet (upgraded) at 65%. On MMLU, DeepSeek R1 leads at 90.8% vs Claude 3.5 Sonnet (upgraded) at 90.5%.