# Mistral Medium 3.1

Mistral Medium 3.1 is an AI model released by Mistral on Aug 12 2025. It has a 128k context window. Tracked results include 65.7% on GPQA Diamond, 40.8% on IFBench and 43.8% on MMMU-Pro.

## Facts

| Field | Value |
| --- | --- |
| Model | Mistral Medium 3.1 |
| Developer | Mistral |
| Release date | Tuesday, Aug 12 2025 |
| Licensing | Closed |
| Context window | 128k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| GPQA Diamond | 65.7% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| IFBench | 40.8% | Lab | Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. |
| MMLU-Pro | 76.8% | Lab | accuracy on the ten-option MMLU-Pro benchmark |
| MMMU-Pro | 43.8% | Lab | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |

## About Mistral Medium 3.1

Mistral Medium 3.1 was released on August 12, 2025 as an update to the commercial Medium 3 model. Mistral described improvements in performance and tone while continuing the line's focus on professional text, coding and multimodal applications.

The model supported a 128K-token context through hosted and enterprise offerings. It was a distinct checkpoint from the May Medium 3 release, even though both occupied the same product tier. The benchmark figures recorded here come from Mistral's later comparison published with Small 4 and should be understood as that evaluation of Medium 3.1, rather than measurements inherited from its predecessor.

## Questions and answers

### When was Mistral Medium 3.1 released?

Mistral Medium 3.1 was released by Mistral on Tuesday, Aug 12 2025.

### Who made Mistral Medium 3.1?

Mistral Medium 3.1 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 Mistral Medium 3.1 get?

Mistral Medium 3.1 reports 4 tracked benchmark scores — GPQA Diamond: 65.7%; IFBench: 40.8%; MMLU-Pro: 76.8%; MMMU-Pro: 43.8%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Mistral Medium 3.1?

Mistral Medium 3.1 has a context window of 128k. Providers may specify separate input and output token limits.

### Is Mistral Medium 3.1 open source?

No. Mistral Medium 3.1 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 Mistral Medium 3.1?

Mistral's previous tracked release was Codestral 25.08 on Jul 30 2025, 13 days earlier. It was followed by Magistral Small 1.2 on Sep 17 2025.


---

Canonical page: https://aireleasetracker.com/model/mistral/mistral-medium-3.1
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.
