Compare AI models

Specifications
Parameters
16B—
Context window
32k1M
Benchmarks
MATH
27.9%77.9%
Overview
CompanyDeepSeekGoogle
Release dateMay 16 2024Sep 24 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Flash-002 leads DeepSeek V2 Lite on 1 of the 1 benchmark they both report (MATH). DeepSeek V2 Lite shipped 131 days before Gemini 1.5 Flash-002, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (DeepSeek V2 Lite) vs 1M (Gemini 1.5 Flash-002). DeepSeek V2 Lite is open weight, while Gemini 1.5 Flash-002 is closed.

On MATH, Gemini 1.5 Flash-002 leads at 77.9% vs DeepSeek V2 Lite at 27.9%.