# Magistral Small 1.1

Magistral Small 1.1 is an AI model released by Mistral on Jul 24 2025. It has 24B parameters, a 40k context window and open weight. Tracked results include 65.78% on GPQA Diamond and 59.17% on LiveCodeBench.

## Facts

| Field | Value |
| --- | --- |
| Model | Magistral Small 1.1 |
| Developer | Mistral |
| Release date | Thursday, Jul 24 2025 |
| Licensing | Open Weight |
| Parameters | 24B |
| Context window | 40k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| LiveCodeBench | 59.17% | Lab | Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. |
| AIME 2024 | 70.52% | Lab | single-answer accuracy on the 2024 invitational mathematics exam without tools |
| AIME 2025 | 62.03% | Lab | single-answer accuracy on the 2025 invitational mathematics exam without tools |
| GPQA Diamond | 65.78% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |

## About Magistral Small 1.1

Magistral Small 1.1 was released on July 24, 2025 as an update to Mistral's downloadable 24B reasoning model. Mistral described broadly similar benchmark performance to version 1.0, with improvements to tone, Markdown and LaTeX formatting, shorter replies to straightforward prompts and fewer generation loops. The update focused on making the model's reasoning and answers easier to use.

Mistral published the weights under Apache 2.0. They supported a 128K-token context, but the company recommended a 40K working limit because performance could degrade beyond it. The recorded AIME, GPQA Diamond and LiveCodeBench v5 results belong to this July checkpoint. Vision input arrived with the later 1.2 update, so Small 1.1 remained a text reasoning model.

## Questions and answers

### When was Magistral Small 1.1 released?

Magistral Small 1.1 was released by Mistral on Thursday, Jul 24 2025.

### Who made Magistral Small 1.1?

Magistral Small 1.1 was built by Mistral. French AI company building open and commercial models. Founded in 2023 by former Meta and DeepMind researchers.

### What benchmark scores did Magistral Small 1.1 get?

Magistral Small 1.1 reports 4 tracked benchmark scores — LiveCodeBench: 59.17%; AIME 2024: 70.52%; AIME 2025: 62.03%; GPQA Diamond: 65.78%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Magistral Small 1.1?

Magistral Small 1.1 has a context window of 40k. Providers may specify separate input and output token limits.

### How many parameters does Magistral Small 1.1 have?

Magistral Small 1.1 is reported at 24B parameters.

### Is Magistral Small 1.1 open source?

Partly. Magistral Small 1.1 is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Magistral Small 1.1?

Mistral's previous tracked release was Devstral Medium on Jul 10 2025, 14 days earlier. It was followed by Magistral Medium 1.1 on Jul 24 2025.


---

Canonical page: https://aireleasetracker.com/model/mistral/magistral-small-1.1
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
