Compare AI models

Specifications
Parameters
—0.5B/1.5B/7B/57B/72B
Context window
256k128k
Benchmarks
HumanEval
86.6%86%
Overview
CompanyMistralQwen
Release dateJan 13 2025Jun 6 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Codestral 25.01 leads Qwen2 on 1 of the 1 benchmark they both report (HumanEval). Qwen2 shipped 221 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Codestral 25.01) vs 128k (Qwen2). Codestral 25.01 is closed, while Qwen2 is open weight.

On HumanEval, Codestral 25.01 leads at 86.6% vs Qwen2 at 86%.