Analysis by budget
What changes by the query's budget
51% of this cut's queries (232 of 451) state no explicit budget. Among the ones that do, we compare three levels: high, medium, and low cost.
Summary
Quique Dacosta tops high-budget queries (18 mentions), followed by Restaurante Mena (15) and La Seu (12); Quique Dacosta and La Seu are also the two names that dominate the fine-dining cuisine category. Restaurante Mena leads both medium and low-cost budgets, suggesting its presence in responses doesn't depend much on how much the person wants to spend.
Data quality notice
Of the 451 calls in this cut, 236 returned capturable text. The gap isn't spread randomly: it's concentrated in three specific day, time-slot, and assistant combinations (detail below) totaling 217 calls, of which only 2 returned text. Those calls completed their run and used tokens, but the text couldn't be recovered due to a capture-pipeline gap, not because the assistant recommended nothing. Every figure on this page counts them toward the total queries, but they can't contribute mentions.
Queries and mentions by budget
"Unspecified" doesn't mean a low budget: it means the query mentions no figure or spend level at all, and it's the majority option in this cut.
Unspecified
232 queries · 698 mentions · 303 distinct restaurants
Most mentioned
- Restaurante Mena (43)
- Casa Federico (32)
- El Pegolí (28)
High
77 queries · 221 mentions · 132 distinct restaurants
Most mentioned
- Quique Dacosta (18)
- Restaurante Mena (15)
- La Seu (12)
Medium
72 queries · 206 mentions · 140 distinct restaurants
Most mentioned
- Restaurante Mena (11)
- Casa Federico (8)
- El Pegolí (8)
Low cost
70 queries · 153 mentions · 92 distinct restaurants
Most mentioned
- Restaurante Mena (8)
- El Baret de Miquel (7)
- La Seu (7)
What we can't claim from this
- We don't analyze the price the assistant itself states in its response (mention.priceLevel) here: that field is free text across three languages, ranging from "€18" to "budget-friendly" or "mid-range", and can't be grouped into clean tiers without inventing a category scheme the data doesn't actually contain.
- Quique Dacosta dominating both fine dining and high budget is an association between two of the experiment's variables, not proof that it's actually the most expensive restaurant in Dénia.
- Nearly half of this cut's queries have no capturable response text (see the data quality notice): mention counts by budget are a floor, not the real total.
Frequently asked questions
Before drawing conclusions by budget
Does an "unspecified" budget mean the assistant assumes I want to spend little?
No. "Unspecified" only means the query mentions no figure or spend level at all, and it's the majority option in this cut (51%, 232 of 451 queries). It doesn't mean the assistant reads the absence of a budget as a request for cheap options.
Why don't you show the exact price the assistant states in its response (€18, budget-friendly, and so on)?
Because that field is free text across three languages, ranging from "€18" to "budget-friendly" or "mid-range". Grouping it into clean tiers would mean inventing a category scheme the data itself doesn't contain, so we'd rather not chart something that would imply a precision that isn't there.
Keep exploring the dataset
This is one of six dimensions we analyze. The rest of the variables, and the full dataset to explore on your own, are on the data page.