Compare AI models

Specifications
Parameters
22B14B
Context window
32k2k
Benchmarks
HumanEval
81.1%32.3%
Overview
CompanyMistralQwen
Release dateMay 29 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Codestral 22B leads Qwen-14B on 1 of the 1 benchmark they both report (HumanEval). Qwen-14B shipped 247 days before Codestral 22B, so benchmark comparisons should account for the intervening progress.

Codestral 22B has 22B parameters, while Qwen-14B has 14B. Context windows are 32k (Codestral 22B) vs 2k (Qwen-14B).

On HumanEval, Codestral 22B leads at 81.1% vs Qwen-14B at 32.3%.