Skip to content
VinumExMachina Atlas of AI in Wine
Select language: Русский
§0

Spec sheet · run v2026-05-04 · OenoBench release_v1.2

How much does a language model actually know about wine?

A bilingual reference on artificial intelligence across viticulture, winemaking, and the wine business — plus OenoBench, the wine knowledge benchmark for large language models.

Instrument record

Run
v2026-05-04
Released
2026-05-04
Paper
OenoBench release_v1.2
Questions
3,266
Evaluations
52,256
Configurations
16
Evaluation spend
$98.33

Domain tags sum to 3,329 and difficulty tags to 3,329 against a corpus of 3,266 — unreconciled, reported as published.

Measured answer

0.974 on questions answerable from what the model already holds
0.703 on questions that require reasoning over context
Δ 0.271 the gap a ranking hides

o3 · OpenAI · best of 16 configurations · 3,266 questions

Fig.01
Fig. 01The corpus, read as a chromatogramcorpus v2026-05-04 · six domains

Chromatogram. 6 peaks, one per wine domain, on a shared baseline with 5 dashed drop lines marking the integration boundaries between them. Each peak's area is proportional to the number of questions carrying that domain tag, and each is labelled with its domain, its question count and its share. The largest is Wine regions at 1,108 questions (33.3%); the smallest is Winemaking at 188 (5.6%). Shares are of the 3,329 domain tags the run publishes, not of its 3,266 questions: 63 questions carry more than one tag. The vertical axis is unlabelled detector signal.

t0 injectWine regions1,10833.3%Grape varieties76623.0%Producers51515.5%Viticulture50215.1%Winemaking1885.6%Wine business2507.5%
Peak area is proportional to the number of questions carrying that domain tag. Peak width and retention order are presentational; drop lines mark the integration boundaries.
Index

Contents

§1 About the project

Scope, method, and how the atlas is written.

§2 Keynote

The long read: what AI in wine actually does, by the numbers.

§3 Benchmarks

§4 Casebook

§5 Research

What is being measured next, and an open door to collaborate.

§6 About the author

Who compiles it, and on what evidence.