Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
Benchmarks
SWE-Bench Verified
49.2%76.2%
GPQA Diamond
71.5%91.9%
Overview
CompanyDeepSeekGoogle
Release dateJan 20 2025Nov 18 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemini 3.0 Pro leads DeepSeek R1 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek R1 shipped 302 days before Gemini 3.0 Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 1M (Gemini 3.0 Pro). DeepSeek R1 is open weight, while Gemini 3.0 Pro is closed.

On SWE-Bench Verified, Gemini 3.0 Pro leads at 76.2% vs DeepSeek R1 at 49.2%. On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs DeepSeek R1 at 71.5%.