Compare AI models

Specifications
Parameters
7B7B
Context window
32k64k
Benchmarks
HumanEval
38.4%83.5%
Overview
CompanyMistralQwen
Release dateMay 22 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 36 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.

Mistral 7B v0.3 has 7B parameters, while CodeQwen1.5 has 7B. Context windows are 32k (Mistral 7B v0.3) vs 64k (CodeQwen1.5).

On HumanEval, CodeQwen1.5 leads at 83.5% vs Mistral 7B v0.3 at 38.4%.