Mistral Large 4, the Mistral AI model in numbers

Mistral Large 4 at a glance

Mistral AI released Mistral Large 4 on October 6, 2026. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. It is a closed model: you access it through an API, from Mistral AI or one of the 14 providers listed on models.dev. It is a very recent release.

We file it under mid-range models (34 models in this category on the site).

What do independent benchmarks say?

According to results published by Epoch AI (checked on October 22, 2026), Mistral Large 4 has a capability index of 79.7 out of 100, computed on 4 benchmarks from our basket.

That puts it at #29 in our weekly model ranking.

• GPQA Diamond (PhD-level science questions): 88.1% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 98.3% — the best tracked model, GPT-5.5 Pro, reaches 100%
• FrontierMath (very hard research-level mathematics): 58.6% — the best tracked model, GPT-6 Astra, reaches 93.7%
• FrontierCode (advanced programming tasks): 39.4% — the best tracked model, Claude Opus 5.5, reaches 54.6%

What it costs

Mistral Large 4 costs $1.36 per million input tokens and $4.18 per million output tokens (developer's price, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.036; a thousand of those tasks, $35.56.

That is in line with mid-range models, whose median output price is $4.38.

Tokens read back from cache cost $0.14 per million, which helps an agent that keeps resending the same context.

To estimate your own budget, use the agent cost calculator.

What it can do

Its context window reaches 1,048,576 tokens, roughly 1,573 pages of text at 500 words per page: enough to load a whole book or a mid-sized codebase. A single answer can run to 262,144 tokens.

It accepts as input: text, image and PDF.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

When to choose it

Given its category, Mistral Large 4 is mainly aimed at a balance between quality and cost, for everyday uses that do not justify a frontier model.

Its very large context window makes it worth considering for analysing large sets of documents in a single request.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

What could replace it?

In the same category, the models closest to Mistral Large 4 are:

• Grok 4.7 (xAI, index 79.9)
• Claude Sonnet 5 (Anthropic, index 79.3)
• Gemini 3.1 Pro Preview (Google DeepMind, index 79.3)
• Gemini 3 Flash Preview (Google DeepMind, index 80.3) — see the comparison