Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Cheapest input
—$0.10Azure
Cheapest output
—$0.40Azure
—$40.00Azure
Benchmarks
MATH-500
97.3%62.3%
DROP
92.282.2
AIME 2024
79.8%29.4%
GPQA Diamond
71.5%50.3%
SimpleQA
30.1%7.6%
MMLU
90.8%80.1%
Overview
CompanyDeepSeekOpenAI
Release dateJan 20 2025Apr 14 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads GPT-4.1 nano on 6 of the 6 benchmarks they both report. DeepSeek R1 shipped 84 days before GPT-4.1 nano, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 1M (GPT-4.1 nano). DeepSeek R1 is open weight, while GPT-4.1 nano is closed.

On MATH-500, DeepSeek R1 leads at 97.3% vs GPT-4.1 nano at 62.3%. On DROP, DeepSeek R1 leads at 92.2 vs GPT-4.1 nano at 82.2. On AIME 2024, DeepSeek R1 leads at 79.8% vs GPT-4.1 nano at 29.4%. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs GPT-4.1 nano at 50.3%. On SimpleQA, DeepSeek R1 leads at 30.1% vs GPT-4.1 nano at 7.6%. On MMLU, DeepSeek R1 leads at 90.8% vs GPT-4.1 nano at 80.1%.