Compare AI models

Specifications
Parameters
671B—
Context window
128k2M
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
LiveCodeBench
40.5%36%
GPQA Diamond
59.1%64.7%
Overview
CompanyDeepSeekGoogle
Release dateDec 26 2024Feb 5 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 and Gemini 2.0 Pro are evenly matched across the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek V3 shipped 41 days before Gemini 2.0 Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 2M (Gemini 2.0 Pro). DeepSeek V3 is open weight, while Gemini 2.0 Pro is closed.

On LiveCodeBench, DeepSeek V3 leads at 40.5% vs Gemini 2.0 Pro at 36%. On GPQA Diamond, Gemini 2.0 Pro leads at 64.7% vs DeepSeek V3 at 59.1%.