Compare AI models

Specifications
Parameters
2B/7B7B
Context window
8k64k
Benchmarks
HumanEval
32.3%83.5%
Overview
CompanyGoogleQwen
Release dateFeb 21 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads Gemma 1 on 1 of the 1 benchmark they both report (HumanEval). Gemma 1 shipped 55 days before CodeQwen1.5, so benchmark comparisons should account for the intervening progress.

Gemma 1 has 2B/7B parameters, while CodeQwen1.5 has 7B. Context windows are 8k (Gemma 1) vs 64k (CodeQwen1.5).

On HumanEval, CodeQwen1.5 leads at 83.5% vs Gemma 1 at 32.3%.