Compare AI models

Specifications
Parameters
7B/13B/34B110B
Context window
16k32k
Benchmarks
HumanEval
48.8%52.4%
Overview
CompanyMetaQwen
Release dateAug 24 2023Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads Code Llama on 1 of the 1 benchmark they both report (HumanEval). Code Llama shipped 245 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Code Llama has 7B/13B/34B parameters, while Qwen1.5-110B has 110B. Context windows are 16k (Code Llama) vs 32k (Qwen1.5-110B).

On HumanEval, Qwen1.5-110B leads at 52.4% vs Code Llama at 48.8%.