# Mistral Large 4

Mistral Large 4 is an AI model released by Mistral on Oct 6 2026. It has 1.05T parameters, a 1M context window and open weight. Tracked results include 80% on BullshitBench v2, 61.7% on DeepSWE 1.1 and 19.7% on FrontierCode 2.0.

## Facts

| Field | Value |
| --- | --- |
| Model | Mistral Large 4 |
| Developer | Mistral |
| Release date | Tuesday, Oct 6 2026 |
| Licensing | Open Weight |
| Parameters | 1.05T |
| Context window | 1M |

## API pricing

All rates in USD per 1,000,000 tokens, pay-as-you-go.

| Tier | Input | Cached input | Output |
| --- | --- | --- | --- |
| Standard | $0.70 | $0.07 | $2.10 |

Verified October 19, 2026 against the first-party source: https://mistral.ai/pricing/api/

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| BullshitBench v2 | 80% | [BullshitBench](https://github.com/petergpt/bullshit-benchmark) | Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. |
| 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. |
| FrontierCode 2.0 | 19.7% | Lab | whether a model’s code changes to open-source repositories would be merged by their maintainers (version 2.0); separate from FrontierCode v1.1 scores |
| 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 | 48 | 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 | 41% | 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. |
| BrowseComp | 84.5% | Lab | Can the AI browse the web and track down hard-to-find answers? 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) |
| threejseval | 1008 | [threejseval](https://threejseval.com/ranking) | Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. |

## About Mistral Large 4

Mistral Large 4 entered public API preview in October 2026 as a natively multimodal mixture-of-experts model for reasoning, coding and agent tasks. The preview was available through Mistral’s API and Mistral Studio. Mistral described training it from scratch on NVIDIA Grace Blackwell hardware in its European datacenters.

Mistral released the weights on October 29, 2026, with a model improved by three more weeks of reinforcement learning since the preview. The release post reported 41% on Terminal-Bench 4.0, up from 28% in the preview, 48% on the Artificial Analysis Coding Agent Index with fewer tokens per task than GLM-5.3, and 84.5% on BrowseComp. It added low, medium and high reasoning modes and cyber guardrails meant to separate defensive work from attacks, while a specialized cybersecurity variant went only to vetted design partners. The weights shipped under the Mistral Ecosystem Open-Weight license, a modified MIT license that requires a separate commercial license for model-as-a-service providers. These were vendor-reported results under Mistral's own setups.

## 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.

### How much does Mistral Large 4 cost?

Mistral Large 4 costs $0.70 per million input tokens and $2.10 per million output tokens through the Mistral API. Cached input is $0.07 per million tokens. Rates are pay-as-you-go API prices verified against Mistral's published pricing on October 19, 2026.

### What benchmark scores did Mistral Large 4 get?

Mistral Large 4 reports 10 tracked benchmark scores — BullshitBench v2: 80%; DeepSWE 1.1: 61.7%; FrontierCode 2.0: 19.7%; SWEAtlas CodeBase QnA: 59.4%; AA Coding Agent Index: 48; Terminal-Bench 4.0: 41%; BrowseComp: 84.5%; AutomationBench: 59.9%; AA-Briefcase v1.1: 1393; threejseval: 1008. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

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

Mistral Large 4 has a context window of 1M. Providers may specify separate input and output token limits.

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

Mistral Large 4 is reported at 1.05T parameters.

### Is Mistral Large 4 open source?

Partly. Mistral Large 4 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 Mistral Large 4?

Mistral's previous tracked release was Mistral Medium 3.5 on Apr 28 2026, 161 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.
