Compare AI models

Specifications
Parameters
236B1B/4B/12B/27B
Context window
128k—
API pricing
Cheapest input
—$0.04DeepInfra
Cheapest output
—$0.08DeepInfra
—$15.00DeepInfra · bf16
Benchmarks
LiveCodeBench
39.7%29.7%
HumanEval
87.2%87.8%
Overview
CompanyDeepSeekGoogle
Release dateJul 24 2024Mar 12 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2-0724 and Gemma 3 are evenly matched across the 2 benchmarks they both report (LiveCodeBench, HumanEval). DeepSeek Coder V2-0724 shipped 231 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2-0724 has 236B parameters, while Gemma 3 has 1B/4B/12B/27B.

On LiveCodeBench, DeepSeek Coder V2-0724 leads at 39.7% vs Gemma 3 at 29.7%. On HumanEval, Gemma 3 leads at 87.8% vs DeepSeek Coder V2-0724 at 87.2%.