Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
SWE-Bench Verified
42%76.2%
GPQA Diamond
59.1%91.9%
Overview
CompanyDeepSeekGoogle
Release dateDec 26 2024Nov 18 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemini 3.0 Pro leads DeepSeek V3 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek V3 shipped 327 days before Gemini 3.0 Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 1M (Gemini 3.0 Pro). DeepSeek V3 is open weight, while Gemini 3.0 Pro is closed.

On SWE-Bench Verified, Gemini 3.0 Pro leads at 76.2% vs DeepSeek V3 at 42%. On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs DeepSeek V3 at 59.1%.