Compare AI models

Specifications
Parameters
236B—
Context window
128k2M
Benchmarks
MATH
71.02%86.5%
Overview
CompanyDeepSeekGoogle
Release dateJun 28 2024Sep 24 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Pro-002 leads DeepSeek V2-0628 on 1 of the 1 benchmark they both report (MATH). DeepSeek V2-0628 shipped 88 days before Gemini 1.5 Pro-002, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V2-0628) vs 2M (Gemini 1.5 Pro-002). DeepSeek V2-0628 is open weight, while Gemini 1.5 Pro-002 is closed.

On MATH, Gemini 1.5 Pro-002 leads at 86.5% vs DeepSeek V2-0628 at 71.02%.