Compare AI models

Specifications
Parameters
236B9B/27B
Context window
128k8k
API pricing
Cheapest input
—$0.65NextBit
Cheapest output
—$0.65NextBit
—$163NextBit · int4
Benchmarks
HumanEval
87.2%51.8%
Overview
CompanyDeepSeekGoogle
Release dateJul 24 2024Jun 27 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 leads Gemma 2 on 1 of the 1 benchmark they both report (HumanEval). Gemma 2 shipped 27 days before DeepSeek Coder V2-0724, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2-0724 has 236B parameters, while Gemma 2 has 9B/27B. Context windows are 128k (DeepSeek Coder V2-0724) vs 8k (Gemma 2).

On HumanEval, DeepSeek Coder V2-0724 leads at 87.2% vs Gemma 2 at 51.8%.