TechPrufer
Get started
Mistral AI
Mistral AI logoMistral AI · Feature trail

Magistral Reasoning Model

2 posts · Jul 2024 – Jun 2025

What this trail covers

Mistral AI introduces Magistral, a new family of reasoning models designed for domain-specific, transparent, and multilingual reasoning. The models are released in two variants: Magistral Small (24B parameters, open-source) and Magistral Medium (enterprise version). Magistral excels in multi-step logic, providing traceable thought processes and high-fidelity reasoning across multiple languages. It is optimized for speed, with Magistral Medium achieving up to 10x faster token throughput in Le Chat. Magistral Small is available for self-deployment under Apache 2.0, and Magistral Medium is available via API on La Plateforme and other cloud providers.

All Mistral AI trails
  1. Magistral | Mistral AIThis post announces Magistral, Mistral AI's first reasoning model family. It details two variants: Magistral Small (24B, open-source, Apache 2.0) and Magistral Medium (enterprise). Key features include domain-specific reasoning, transparent chain-of-thought across languages, and optimized speed (10x faster token throughput for Medium in Le Chat). Performance metrics on AIME2024 are provided. The post also references a supporting research paper and highlights applications in business strategy, regulated industries, systems engineering, and content creation.
  2. MathΣtral | Mistral AIIntroduces MathΣtral, a specialized 7B parameter model derived from Mistral 7B, focusing on advanced mathematical problems requiring complex, multi-step logical reasoning. MathΣtral achieves state-of-the-art reasoning capacities in its size category across industry-standard benchmarks like MATH (56.6%) and MMLU (63.47%), demonstrating significant performance improvements over its base model in STEM subjects. It can achieve even better results with increased inference-time computation, such as 68.37% on MATH with majority voting and 74.59% with a strong reward model among 64 candidates. The model is released under an Apache 2.0 license and is available via HuggingFace, mistral-inference, and mistral-finetune.