Compare AI models

Specifications
Parameters
1.5B/7B/8B/14B/32B/70B—
Context window
—128k
Benchmarks
MATH-500
94.5%90%
AIME 2024
70%70%
GPQA Diamond
65.2%60%
Overview
CompanyDeepSeekOpenAI
Release dateJan 20 2025Sep 12 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 Distill leads o1-mini on 2 of the 3 benchmarks they both report (MATH-500, AIME 2024, GPQA Diamond). o1-mini shipped 130 days before DeepSeek R1 Distill, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 Distill is open weight, while o1-mini is closed.

On MATH-500, DeepSeek R1 Distill leads at 94.5% vs o1-mini at 90%. On AIME 2024, both models score 70%. On GPQA Diamond, DeepSeek R1 Distill leads at 65.2% vs o1-mini at 60%.