Compare AI models

Specifications
Parameters
47B7B
Context window
32k64k
Benchmarks
HumanEval
40.2%83.5%
Overview
CompanyMistralQwen
Release dateDec 8 2023Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads Mixtral 8×7B on 1 of the 1 benchmark they both report (HumanEval). Mixtral 8×7B shipped 130 days before CodeQwen1.5, so benchmark comparisons should account for the intervening progress.

Mixtral 8×7B has 47B parameters, while CodeQwen1.5 has 7B. Context windows are 32k (Mixtral 8×7B) vs 64k (CodeQwen1.5).

On HumanEval, CodeQwen1.5 leads at 83.5% vs Mixtral 8×7B at 40.2%.