# How Austrian Academy of Sciences uses Mistral

**600M words** words of historical Greek texts in Apollo's

As published on [mistral.ai](https://mistral.ai/customers/austrian-academy-of-sciences/), May 2026. Captured by usedby on 2026-10-02.

- Company: [Austrian Academy of Sciences](https://www.usedby.ai/companies/austrian-academy-of-sciences.md)
- Tool: [Mistral](https://www.usedby.ai/tools/mistral.md)
- Teams: Austrian Archaeological Institute

## What the story says

The Austrian Academy of Sciences works with Mistral to build Apollo, a custom large language model for Ancient Greek. Researchers use it to reconstruct damaged texts and find thematic connections across large collections of inscriptions and papyri.

Summary written by usedby from the source page, in English. The figures are those of Mistral and Austrian Academy of Sciences, not ours.

> Apollo helps researchers reconstruct damaged texts and accelerate discoveries that once took years into hours, with future phases planned to support semantic search and handwritten inscription decipherment.

> AI and ancient languages are not a contradiction. Apollo will amplify our understanding of history by unlocking the secrets of fragmentary texts.
>
> Heinz Faßmann, President, Austrian Academy of Sciences

## What usedby checked

We compared the story with its live page on 2026-10-03.

- Checked: the figure 600M words is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of Austrian Academy of Sciences.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Austrian Academy of Sciences uses Mistral. Confirmed line. Latest check across sources: 2026-10-02.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/austrian-academy-of-sciences-mistral · How we check: https://www.usedby.ai/methodology