# Magistral Medium 1.1

Magistral Medium 1.1 is an AI model released by Mistral on Jul 24 2025. It has a 40k context window. Tracked results include 71.46% on GPQA Diamond and 59.35% on LiveCodeBench.

## Facts

| Field | Value |
| --- | --- |
| Model | Magistral Medium 1.1 |
| Developer | Mistral |
| Release date | Thursday, Jul 24 2025 |
| Licensing | Closed |
| Context window | 40k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| LiveCodeBench | 59.35% | 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 | 72.03% | Lab | single-answer accuracy on the 2024 invitational mathematics exam without tools |
| AIME 2025 | 60.99% | Lab | single-answer accuracy on the 2025 invitational mathematics exam without tools |
| GPQA Diamond | 71.46% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |

## About Magistral Medium 1.1

Magistral Medium 1.1 was announced in Mistral's July 24, 2025 model update as the hosted counterpart to Magistral Small 1.1. It continued the Medium reasoning line introduced in June, giving API users an updated model for tasks that benefited from longer deliberation.

The release had a documented 40K-token context and remained a commercial service without publicly downloadable weights. Mistral evaluated it separately from both the original Medium and the smaller July checkpoint. The version suffix therefore matters when comparing reasoning results, especially across the later September update that also added image understanding.

## Questions and answers

### When was Magistral Medium 1.1 released?

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

### Who made Magistral Medium 1.1?

Magistral Medium 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 Medium 1.1 get?

Magistral Medium 1.1 reports 4 tracked benchmark scores — LiveCodeBench: 59.35%; AIME 2024: 72.03%; AIME 2025: 60.99%; GPQA Diamond: 71.46%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

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

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

### Is Magistral Medium 1.1 open source?

No. Magistral Medium 1.1 is a closed model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

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

Mistral's previous tracked release was Magistral Small 1.1 on Jul 24 2025. It was followed by Codestral 25.08 on Jul 30 2025.


---

Canonical page: https://aireleasetracker.com/model/mistral/magistral-medium-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.
