Compare AI models

Specifications
Parameters
1B/4B/12B/27B7B
Context window
—64k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.05Parasail—
$10.50Parasail · bf16—
Benchmarks
HumanEval
87.8%83.5%
Overview
CompanyGoogleQwen
Release dateMar 12 2025Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 3 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 330 days before Gemma 3, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while CodeQwen1.5 has 7B.

On HumanEval, Gemma 3 leads at 87.8% vs CodeQwen1.5 at 83.5%.