# Magistral Medium Magistral Medium is a proprietary reasoning model developed by [[Mistral AI]], released in June 2025. It is the more powerful, enterprise-oriented variant of the Magistral family, Mistral's first reasoning model line. The model scored 73.6% on AIME2024, and 90% with majority voting @64, outperforming its open-weight sibling [[Magistral Small]]. It is designed for transparent, multi-step reasoning with traceable chain-of-thought that users can follow and verify. Magistral Medium excels across professional domains including legal research, financial forecasting, software development, and creative writing. It supports native reasoning in multiple languages and alphabets, including English, French, Spanish, German, Italian, Arabic, Russian, and Simplified Chinese. With Flash Answers in Le Chat, Magistral Medium achieves up to 10x faster token throughput than most competitors, enabling real-time reasoning at scale. It is available via Le Chat, La Plateforme API, Amazon SageMaker, and soon on IBM WatsonX, Azure AI, and Google Cloud Marketplace. ## References - https://mistral.ai/news/magistral - https://arxiv.org/pdf/2506.10910 ## Related - [[Mistral AI]] - [[Magistral Small]] - [[Large Language Models (LLMs)]] - [[Mistral Small 4]]