Compare AI models

Specifications
Parameters
—671B
Context window
200k128k
Benchmarks
GPQA Diamond
40.4%71.5%
MMLU
81.5%90.8%
Overview
CompanyAnthropicDeepSeek
Release dateMar 4 2024Jan 20 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Claude 3 Sonnet on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU). Claude 3 Sonnet shipped 322 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Sonnet) vs 128k (DeepSeek R1). Claude 3 Sonnet is closed, while DeepSeek R1 is open weight.

On GPQA Diamond, DeepSeek R1 leads at 71.5% vs Claude 3 Sonnet at 40.4%. On MMLU, DeepSeek R1 leads at 90.8% vs Claude 3 Sonnet at 81.5%.