# What is Magistral, Mistral's first reasoning model?

Date: 2025-06-11 · Author: Robert Scales · https://guidetoartificialintelligence.com/en/learn/what-is-mistral-magistral/

**Answer:** Magistral is Mistral AI's first family of reasoning models, released on June 10, 2025, in two versions, an open 24-billion-parameter Magistral Small that anyone can download and a more capable Magistral Medium for businesses. Both think step by step before answering, and Mistral built them to reason in the user's own language and show a thought process people can follow and check.

Yesterday, Tuesday, June 10, 2025, the French company Mistral AI announced **Magistral**, its first reasoning model. Reasoning models, a category OpenAI opened with o1 last year and DeepSeek popularized with R1 in January, write out a chain of intermediate steps before giving their final answer. That extra thinking makes them better at math, logic, code and planning.

Mistral released Magistral in two versions at once, together with a research paper describing how it trained them. Its emphasis is on three things the company says early reasoning models handle poorly: depth in professional fields, transparency, and consistent reasoning in languages other than English.

## What Mistral released

| | Magistral Small | Magistral Medium |
|---|---|---|
| Size | 24 billion parameters | Not disclosed |
| Built on | Mistral Small 3 | Mistral Medium 3 |
| Access | Free download (Apache 2.0 license) on Hugging Face | Preview in Le Chat and the API; Amazon SageMaker, IBM watsonx |
| AIME 2024 (single try) | 70.7% | 73.6% |
| AIME 2024 (majority of 64 tries) | 83.3% | 90% |

**AIME** is the American Invitational Mathematics Examination, a hard competition for high-school students often used to test reasoning models. "Majority of 64 tries" means the model answers each problem 64 times and the most common answer counts, a technique that raises scores but costs more computing. A **parameter** is one of the adjustable numbers inside a model; 24 billion is small enough for a single powerful machine.

In Le Chat, Mistral's chatbot, Magistral Medium powers a new **Think mode**. Combined with Flash Answers, a speed feature, Mistral says it produces text up to ten times faster than most competitors.

## How Magistral was trained

The paper explains the method in detail. Mistral started from Mistral Medium 3, an ordinary model released in May, and taught it to reason using only **reinforcement learning** (RL): the model attempts problems, its answers are scored automatically, and it gradually shifts toward whatever earns higher scores. Unlike some rivals, Mistral did not copy reasoning examples from another lab's reasoning model to give it a head start. The company says RL alone improved Medium 3's single-try AIME score by nearly 50%.

The key is a **verifiable reward**, a score a computer can check without human judgment. For each problem the model answered, Mistral's system awarded points roughly like this:

| Check | Reward |
|---|---|
| Wrong format (thinking not enclosed in the required tags, no boxed math answer, no code block) | 0, and grading stops |
| Correct format | 0.1 |
| Math answer matches the reference, or code passes 20 test cases | +0.9 |
| Problem, reasoning and answer all in the same language | +0.1 |
| Answer runs close to the length limit | small penalty |

The training algorithm, a modified version of **GRPO** (Group Relative Policy Optimization), has the model answer the same problem several times and compares the answers within that group. Answers that beat the group average are reinforced. Think of a teacher who grades a stack of attempts at one exercise on a curve, rather than against an outside expert's opinion.

The language reward fixes a quirk. Without it, Mistral found the model's reasoning drifted into a mix of English, Chinese and Russian. Translating a tenth of the training problems into French, Spanish, Italian, German, Chinese and Russian, and rewarding matching languages, was enough to keep the model thinking in the user's language. The authors report it then managed this even in languages it was not specifically trained on.

## A worked example

Because Magistral reasons in your language and shows its steps, it suits problems where you want to check the logic. A prompt in French might look like this:

```prompt
Une boulangerie vend des croissants à 1,80 € et des pains au chocolat
à 2,10 €. Samedi, elle a vendu 240 viennoiseries pour 465 €.
Combien de croissants a-t-elle vendus ? Montre ton raisonnement.
```

A reasoning model would set up two equations (croissants plus pains au chocolat equals 240; their prices times quantities equal 465), solve them and find 130 croissants and 110 pains au chocolat, with each step written in French that you can verify.

> **Try it:** Ask Magistral, in your own language, a multi-step problem you already know the answer to, such as a budget or a scheduling puzzle. Read the reasoning, not just the final answer, and find the first step where you would have done something differently.

## Why it matters

Magistral completes Mistral's lineup: the company now has a reasoning option alongside its general models, and one of the two versions is fully open. Developers can download Magistral Small, inspect how it reasons and build on it, which Mistral explicitly invites.

Mistral also aims it at **regulated industries** such as law, finance, healthcare and government, where a traceable chain of reasoning can help with audits. It lists uses from risk assessment and delivery planning to software design and creative writing.

TechCrunch offers a sober view: Mistral has been slower than some leading labs to ship a reasoning model, and by Mistral's own charts Magistral Medium trails Claude Opus 4 (from Anthropic) and Gemini 2.5 Pro (from Google) on several science, math and coding tests. Its distinctive selling points are speed, language coverage and openness rather than top scores. Mistral says it plans to update the models quickly.

## How can you try Magistral today?

The quickest way is Le Chat, Mistral's chatbot, on the web or its mobile apps. A preview of Magistral Medium powers its Think mode; switch it on and ask a question that benefits from step-by-step reasoning. Developers can call the same preview through Mistral's La Plateforme API, or through Amazon SageMaker and IBM watsonx.

If you prefer to run a model yourself, Magistral Small is on Hugging Face under the name Magistral-Small-2506, with the permissive Apache 2.0 license that allows commercial use. You will need a computer with a capable graphics card or plenty of memory to run a 24-billion-parameter model comfortably.

Whichever version you use, give it problems with clear right answers first, compare its reasoning against your own, and remember that the benchmark figures so far come from Mistral itself.

## Sources

- Magistral: https://mistral.ai/news/magistral
- Magistral: https://mistral.ai/static/research/magistral.pdf
- Mistral releases a pair of AI reasoning models: https://techcrunch.com/2025/06/10/mistral-releases-a-pair-of-ai-reasoning-models/