Compare AI models

Specifications
Parameters
7B/13B/34B14B
Context window
16k2k
Benchmarks
HumanEval
48.8%32.3%
Overview
CompanyMetaQwen
Release dateAug 24 2023Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Code Llama leads Qwen-14B on 1 of the 1 benchmark they both report (HumanEval). Code Llama shipped 32 days before Qwen-14B, so benchmark comparisons should account for the intervening progress.

Code Llama has 7B/13B/34B parameters, while Qwen-14B has 14B. Context windows are 16k (Code Llama) vs 2k (Qwen-14B).

On HumanEval, Code Llama leads at 48.8% vs Qwen-14B at 32.3%.