Compare AI models

Specifications
Parameters
—0.5B/1.5B/3B/7B/14B/32B/72B
Context window
128k128k
API pricing
Cheapest input
—$0.288DeepInfra
Cheapest output
—$0.32DeepInfra
—$92.00DeepInfra · fp8
Benchmarks
LiveCodeBench
75%55.5%
Overview
CompanyMistralQwen
Release dateSep 17 2025Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Medium 1.2 leads Qwen2.5 on 1 of the 1 benchmark they both report (LiveCodeBench). Qwen2.5 shipped 363 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Medium 1.2) vs 128k (Qwen2.5). Magistral Medium 1.2 is closed, while Qwen2.5 is open weight.

On LiveCodeBench, Magistral Medium 1.2 leads at 75% vs Qwen2.5 at 55.5%.