Compare AI models

Specifications
Parameters
236B2B/7B
Context window
128k8k
Benchmarks
HumanEval
84.76%32.3%
MATH
71.02%24.3%
Overview
CompanyDeepSeekGoogle
Release dateJun 28 2024Feb 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Gemma 1 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Gemma 1 shipped 128 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Gemma 1 has 2B/7B. Context windows are 128k (DeepSeek V2-0628) vs 8k (Gemma 1).

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Gemma 1 at 32.3%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Gemma 1 at 24.3%.