Compare AI models

Specifications
Parameters
7B/13B/33B/65B7B
Context window
2k64k
Benchmarks
HumanEval
23.7%83.5%
Overview
CompanyMetaQwen
Release dateFeb 24 2023Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads LLaMA 1 on 1 of the 1 benchmark they both report (HumanEval). LLaMA 1 shipped 417 days before CodeQwen1.5, so benchmark comparisons should account for the intervening progress.

LLaMA 1 has 7B/13B/33B/65B parameters, while CodeQwen1.5 has 7B. Context windows are 2k (LLaMA 1) vs 64k (CodeQwen1.5).

On HumanEval, CodeQwen1.5 leads at 83.5% vs LLaMA 1 at 23.7%.