Skip to content

Magistral Medium 2509

Magistral Medium 2509 is Mistral AI's reasoning model for enterprise use, with 73.6% on AIME 2024 (single-sample), traceable chain-of-thought, and multilingual reasoning across eight languages.

ReasoningVision (Image)
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'mistral/magistral-medium',
  prompt: 'Why is the sky blue?'
})
OverviewPlaygroundAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

Frequently Asked Questions

  • What is Magistral Medium 2509's AIME 2024 score?

    73.6% single-sample, and 90% with majority voting at 64 samples.

  • What is traceable chain-of-thought reasoning?

    Magistral Medium 2509 exposes each reasoning step rather than returning only a final answer. Users and auditors can follow the inferential process from question to conclusion.

  • Which languages does Magistral Medium 2509 support for reasoning?

    English, French, Spanish, German, Italian, Arabic, Russian, and Simplified Chinese.

  • How does Magistral Medium 2509 differ from Magistral Small?

    Magistral Medium 2509 is the larger variant. Magistral Small is a 24B open-source model under Apache 2.0 that scores 70.7% on AIME 2024. Choose Magistral Small when you prioritize lower cost over the extra 2.9 points on AIME 2024 single-sample.

  • Can Magistral Medium 2509 be used for software engineering tasks?

    Yes. Software engineering is one of its listed domain expertise areas alongside business strategy and regulated industries.

  • Does Magistral Medium 2509 have a reasoning budget or thinking token parameter?

    Mistral AI hasn't publicly disclosed configurable thinking budgets for Magistral Medium 2509.