Compare AI models

Specifications
Parameters
671B8B
Context window
128k1M
Benchmarks
MMLU
90.8%68.1%
Overview
CompanyDeepSeekGoogle
Release dateJan 20 2025Oct 3 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Gemini 1.5 Flash-8B on 1 of the 1 benchmark they both report (MMLU). Gemini 1.5 Flash-8B shipped 109 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Gemini 1.5 Flash-8B has 8B. Context windows are 128k (DeepSeek R1) vs 1M (Gemini 1.5 Flash-8B). DeepSeek R1 is open weight, while Gemini 1.5 Flash-8B is closed.

On MMLU, DeepSeek R1 leads at 90.8% vs Gemini 1.5 Flash-8B at 68.1%.