Original research · ArribaIA
Which Dénia restaurant the AI recommends
We send thousands of real queries to ChatGPT and other assistants asking where to eat in Dénia, save every full response, and extract which restaurants get mentioned, in what position, and with what attributes. It's not a survey or a list of our own favorites: it's a measurement with a public methodology.
We're still analyzing the data collected so far. Once we lock in a ranking publication date, you'll see it here.
What we're studying
How Dénia restaurants show up in AI responses
The question this study answers is specific: when someone asks ChatGPT or another AI assistant where to eat in Dénia, which restaurants does it cite, in what order, and with what information.
To answer it, we automate sending realistic queries (the kind a person would actually type while looking for a restaurant, not loose keywords), save each assistant's full response, and use a second model as a referee to extract the restaurants mentioned, their position, and their attributes.
What this study is not
- It is not a customer survey or a popularity vote.
- It is not an editorial ranking based on the ArribaIA team's own taste.
- It doesn't measure food or service quality: it measures visibility and recommendation frequency in the responses of the AI assistants analyzed, under this experiment's specific conditions.
The experiment in numbers
Where the experiment stands right now
We publish the experiment's real status as it moves forward. We don't show any results figure until it's verified.
Status
In progress: continuous collection and analysis underway
Queries sent so far
Thousands, exact count pending a closing count
Data collection
Continuous, no fixed end date
Current phase
Analyzing the data collected so far
Still to publish
Visibility ranking and an explorable dataset
How it's done
The experiment's design, summarized
The full design, with every variable justified and its limits stated, lives in the methodology. This is the summary for anyone who only needs the general frame.
Automated queries
A system generates and sends realistic questions to each assistant ('where can I get rice for dinner in Dénia tonight?', for example), not keyword lists.
Crossed variables
Each query combines cuisine, search intent, language, budget, and Dénia zone, to cover how people actually ask, not a single repeated script.
Time slots
Queries are spread across several time slots of the day, Madrid time, to see whether the time of the query changes the response.
Extraction with a referee model
A second model reads each response and extracts which restaurants are mentioned, at what position, with what attributes, and with what tone. This extraction can contain errors, and we explain that in the methodology.
Normalization
Extracted names are normalized deterministically so the same restaurant doesn't get counted twice over a spelling variation.
Articles and analysis
What we'll publish from the data
Each piece analyzes a different dimension of the same dataset. The ones with real content already are linked; the rest go live once there's verified data to show, without pre-announcing figures.
How we measure GEO ranking for Dénia restaurants
Full design of the Dénia restaurants GEO study: variables, models, extraction process, definitions, and limitations. Data collection is continuous; the ranking publishes once we close a verified cut of the data.
ReadIs showing up in the API the same as showing up in the ChatGPT interface?
Why measuring via API isn't exactly the same as measuring with an AI assistant's consumer interface, with each provider's own documentation as evidence.
ReadDénia restaurants GEO visibility ranking
Will rank Dénia restaurants by mention count and average position in the responses of the AI assistants analyzed, with the exact date and conditions of the measurement. It is not a quality ranking or a best-of list: it is a GEO visibility ranking, under this experiment's conditions.
Coming soonDénia GEO study statistics and data
This is where you'll be able to explore the experiment's dataset: filter by cuisine, intent, language, budget, and zone, see aggregated statistics, and draw your own conclusions from the same raw data we used, not from an already-interpreted summary.
Coming soonAnalysis by cuisine type
Do restaurants from certain cuisines show up more often in AI responses? This piece compares mention frequency and average position across the experiment's cuisine types: Japanese, Italian, Valencian rice dishes, seafood, fine dining, tapas, and the rest.
Coming soonAnalysis by time slot
The time slot a query is sent in (morning, midday, afternoon, or evening, Madrid time) can change which restaurant the AI cites. This piece compares the four slots to check.
Coming soonAnalysis by search intent
Asking where to book tonight isn't the same as asking where to eat sometime during next month's trip. This piece compares the experiment's four intents (immediate booking, future booking, discovery, and situational queries) to see whether the AI answers differently depending on what the person needs in that moment.
Coming soonAnalysis by budget
When someone states a budget in their question, does the answer change? This piece compares queries with an explicit budget against those without one, and how much price detail each assistant gives.
Coming soonComparing the AI assistants
The AI assistants analyzed don't have to agree with each other. This piece measures how much their recommendations overlap, whether they agree on position, and where they differ, without generalizing beyond the models and versions actually studied.
Coming soonChatGPT with web search vs. without it
Turning web search on or off changes what the same model answers. This piece documents those differences with concrete examples: how current the information is, whether citations and links appear, and cases of incorrect claims when the model answers without searching.
Coming soonWhy it matters
Why this matters to a Dénia restaurant
Asking ChatGPT where to eat, instead of opening a map or a list of reviews, isn't unusual behavior anymore. If a restaurant doesn't show up in those answers, or shows up with wrong information, it loses a recommendation channel that no longer depends solely on Google.
This study doesn't promise a formula for ranking better in ChatGPT: it documents, with a public methodology, which restaurants show up today, how often, and under what conditions, so anyone, restaurants included, can review the data and draw their own conclusions.
Generative search doesn't replace traditional search, it adds a different layer: a written answer instead of a list of links. Understanding that difference is the starting point of the discipline ArribaIA calls GEO.
Limitations we acknowledge upfront
- Any figure we publish is a snapshot of one specific moment: collection keeps moving after that snapshot, so the full dataset is always bigger than whatever was last published.
- Assistants can answer the same question differently at a different moment.
- Automated restaurant extraction can make mistakes; we document how we mitigate them and which we accept.
- A provider's API isn't necessarily identical to what a person sees using its web interface, which we cover in detail in GEO UI vs API.
Methodology and transparency
You can check exactly how we measure this
We publish the full experimental design before we have a closed ranking: variables, collection cadence, models, extraction process, and limitations. If anything in the final ranking doesn't match this, it's our mistake and we correct it.
Go to the methodologyFrequently asked questions
This usually answers questions before you write to us
Is this a ranking of the best restaurants in Dénia?
No. It measures how often and in what position each restaurant shows up in the responses of the AI assistants analyzed, under this experiment's conditions. A restaurant can be excellent and not show up, or show up and not be the best fit for everyone.
Did you survey customers or collect reviews for this study?
No. The entire dataset comes from automated queries to AI assistants and the extraction of their responses. There's no human opinion, survey, or vote in the measurement process.
My restaurant doesn't show up, does that mean it has bad GEO?
Not necessarily. Showing up or not in this specific experiment depends on many variables (what was asked, in what language, with what budget) and on how each assistant builds its answer. It's a signal, not a complete diagnosis.
Can I ask you to analyze my restaurant or my sector?
Yes. The contact form has a specific option for that. This study's architecture is built so it can be repeated for another sector or another city.
Restaurants, press, and researchers
If your restaurant shows up in the study, if it doesn't and you want to understand why, or if you work in research and want to collaborate, write to us through the study's form.