Compare AI models

Specifications
Parameters
16B8B
Context window
32k1M
Benchmarks
MATH
27.9%35.9%
MMLU
55.7%68.1%
Overview
CompanyDeepSeekGoogle
Release dateMay 16 2024Oct 3 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Flash-8B leads DeepSeek V2 Lite on 2 of the 2 benchmarks they both report (MATH, MMLU). DeepSeek V2 Lite shipped 140 days before Gemini 1.5 Flash-8B, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 Lite has 16B parameters, while Gemini 1.5 Flash-8B has 8B. Context windows are 32k (DeepSeek V2 Lite) vs 1M (Gemini 1.5 Flash-8B). DeepSeek V2 Lite is open weight, while Gemini 1.5 Flash-8B is closed.

On MATH, Gemini 1.5 Flash-8B leads at 35.9% vs DeepSeek V2 Lite at 27.9%. On MMLU, Gemini 1.5 Flash-8B leads at 68.1% vs DeepSeek V2 Lite at 55.7%.