Compare AI models

Specifications
Parameters
671B—
Context window
128k200k
Benchmarks
MATH-500
97.3%97.5%
DROP
92.277.7
GPQA Diamond
71.5%77.6%
SimpleQA
30.1%20.2%
MMLU
90.8%90%
Overview
CompanyDeepSeekOpenAI
Release dateJan 20 2025Apr 16 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads o4-mini on 3 of the 5 benchmarks they both report. DeepSeek R1 shipped 86 days before o4-mini, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 200k (o4-mini). DeepSeek R1 is open weight, while o4-mini is closed.

On MATH-500, o4-mini leads at 97.5% vs DeepSeek R1 at 97.3%. On DROP, DeepSeek R1 leads at 92.2 vs o4-mini at 77.7. On GPQA Diamond, o4-mini leads at 77.6% vs DeepSeek R1 at 71.5%. On SimpleQA, DeepSeek R1 leads at 30.1% vs o4-mini at 20.2%. On MMLU, DeepSeek R1 leads at 90.8% vs o4-mini at 90%.