Compare AI models

Specifications
Parameters
7B110B
Context window
64k32k
Benchmarks
HumanEval
83.5%52.4%
Overview
CompanyQwenQwen
Release dateApr 16 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads Qwen1.5-110B on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 9 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

CodeQwen1.5 has 7B parameters, while Qwen1.5-110B has 110B. Context windows are 64k (CodeQwen1.5) vs 32k (Qwen1.5-110B).

On HumanEval, CodeQwen1.5 leads at 83.5% vs Qwen1.5-110B at 52.4%.