Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
256k256k
Benchmarks
LiveCodeBench
37.9%78.9%
Overview
CompanyMistralQwen
Release dateJan 13 2025Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads Codestral 25.01 on 1 of the 1 benchmark they both report (LiveCodeBench). Codestral 25.01 shipped 407 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Codestral 25.01) vs 256k (Qwen3.5 Medium). Codestral 25.01 is closed, while Qwen3.5 Medium is open weight.

On LiveCodeBench, Qwen3.5 Medium leads at 78.9% vs Codestral 25.01 at 37.9%.