# Mistral Large 4

Mistral Large 4 is an AI model released by Mistral on Oct 6 2026. It has 1T parameters and a 512k context window. Tracked results include 59.9% on AutomationBench, 61.7% on DeepSWE 1.1 and 59.4% on SWEAtlas CodeBase QnA.

## Facts

| Field | Value |
| --- | --- |
| Model | Mistral Large 4 |
| Developer | Mistral |
| Release date | Tuesday, Oct 6 2026 |
| Licensing | Closed |
| Parameters | 1T |
| Context window | 512k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| DeepSWE 1.1 | 61.7% | Lab | Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. |
| SWEAtlas CodeBase QnA | 59.4% | Lab | Questions about how an unfamiliar codebase actually works — where something is handled, what a change would touch — answered by reading the repository rather than editing it. Tests understanding rather than patch-writing. Higher is better. |
| AA Coding Agent Index | 49.8 | Lab | Artificial Analysis' overall score for coding agents, combining three coding benchmarks with what each run costs and how many tokens it burns. It rates a model paired with a particular agent harness rather than the model alone, so the same model scores differently in different tools. Higher is better. |
| Terminal-Bench 4.0 | 28.3% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. |
| AutomationBench | 59.9% | Lab | Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. |
| AA-Briefcase v1.1 | 1393 | Lab | Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) |

## About Mistral Large 4

Mistral Large 4, released October 6, 2026 as a public API preview, was the fourth generation of the flagship line Mistral opened in February 2024, and the lab's largest model at the time: a natively multimodal mixture-of-experts with 1 trillion total and 49 billion active parameters, a 512K-token context window and up to 256K tokens of output. Mistral pitched it at reasoning, coding and agentic work, said it had been trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in the lab's own European datacenters, and promised open weights by the end of the month. Until then the preview was also red-teamed with security firms, vetted partners and state authorities, which got a less heavily moderated build with expanded cyber capabilities.

Cybersecurity was the lead claim. Mistral said the model was among the top five on the Artificial Analysis Cyber Index, reported 93% on Cybench and 82% on the index's reproduce-and-patch test, which it said was the highest of any model, and pointed out that several closed models scored near zero there because they refused the task. On coding it scored 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas Codebase QnA and 28.3% on Terminal-Bench 4.0 in Artificial Analysis runs made before the harness went public, for 49.8 on the Coding Agent Index, ahead of DeepSeek-V4-Pro-0813 and Qwen3.8-Max on Mistral's chart. It also posted 59.9% on AutomationBench and 1,393 Elo on AA-Briefcase. Mistral framed the open weights and self-hosting as the point for security teams, who could run the model under their own policies without depending on a provider's refusals, and said the release would become the base for a new generation of specialised Mistral models.

## Questions and answers

### When was Mistral Large 4 released?

Mistral Large 4 was released by Mistral on Tuesday, Oct 6 2026.

### Who made Mistral Large 4?

Mistral Large 4 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 Large 4 get?

Mistral Large 4 reports 6 tracked benchmark scores — DeepSWE 1.1: 61.7%; SWEAtlas CodeBase QnA: 59.4%; AA Coding Agent Index: 49.8; Terminal-Bench 4.0: 28.3%; AutomationBench: 59.9%; AA-Briefcase v1.1: 1393. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data. It holds the best score among all models tracked here on AutomationBench.

### What is the context window of Mistral Large 4?

Mistral Large 4 has a context window of 512k. That is the maximum amount of input plus output the model can hold in a single request.

### How many parameters does Mistral Large 4 have?

Mistral Large 4 is reported at 1T parameters.

### Is Mistral Large 4 open source?

No. Mistral Large 4 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 Large 4?

Mistral's previous tracked release was Mistral Medium 3.5 on Apr 29 2026, 160 days earlier. It is the most recent Mistral model tracked on AI Release Tracker.


---

Canonical page: https://aireleasetracker.com/model/mistral/mistral-large-4
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.