Skip to content
Research brief · AI search visibilitySeptember 2026

Four AIs, one question, four different answers

Four leading AI engines chose the same top local business in 4 percent of shared tests. Their disagreement often starts with the businesses and pages each one considers.

An analysis of 491,972 shared local query-market cases from February through August 2026.

AI search · local recommendations · citation mix · business profiles · reviews · schema

4%
query share with the same top choice
18.3%
three-or-four agreement rate
48%
query share with four different top choices
91%
when engines agreed, the winner's own site was cited
The short version

Each engine starts with a different consideration set. Inside those sets, ratings, review depth, recent activity, and clear business data help shape which name reaches the top.

What to do. Make every location easy to find on its website, profile, and key directories. Then keep reviews, replies, photos, and posts current.

How to read the study

A consideration set is the group of businesses an engine names for one local question. Agreement measures whether at least three engines place the same business first.

The study used unbranded local recommendation prompts in the form “What are the top 10 [category] near [neighborhood]?” The same prompt and place were tested across all four engines.

The panel covered 3,569 keywords and 2.05 million local questions. The core comparison uses the 491,972 cases asked of all four engines across 124,820 market observations each month. Cases with fewer than four engines were excluded from the consensus comparison.

Finding 01

The same question rarely produces the same winner

A factual question may converge on one answer. A subjective local recommendation can vary even across repeated runs of the same model. Across the common panel, all four engines chose the same top business in 4 percent of cases. They chose four different top businesses in 48 percent.

How Often the Top Choice MatchesYext Research · Fig 1 · February to August 2026
Same top choice 4% Four different top choices 48% 0% 50%

A full split happened 12 times as often as a full match. Sample 491,972 shared local query-market cases.

The examples show the range the aggregate hides. One query has no shared first pick, two have partial agreement, and one is unanimous. The same location sometimes appeared under different names across engines. The matching step resolved those variations before distinct businesses were counted.

Four Queries Show Four Levels of AgreementYext Research · Fig 2 · February to August 2026

Auto sunroof shops near Winnetka

19 of 26

Nineteen businesses appeared in 26 results. Each engine chose a different name first.

Waterproofing near Sedalia

14 of 27

Affordable Foundation Repair ranked first in two engines, second in one, and fourth in one.

Oil changes near Findlay

19 of 28

Valvoline ranked first in three engines and third in the fourth.

Tire shops near Killeen

22 of 29

Discount Tire ranked first in all four, but the lists still contained 22 distinct businesses across 29 results.

Agreement can change from none to unanimous while each list still contains many different businesses. Four observed query examples with name-and-place deduplication.

23

Across the four lists, a query produced an average of 23 different businesses. Each engine returned about 7 businesses on average, even when asked for 10.

Finding 02

Why candidate pools matter

A companion Google local search surfaced about 37 businesses in a typical market. Each AI engine named about 7, and the union across all four averaged 23. Agreement generally fell as the broader option pool grew, although category patterns did not move in perfect lockstep.

Three-or-Four Engine Agreement by MarketYext Research · Fig 3 · February to August 2026
Market densityOverallRetailFinancialServicesHealthcareHospitalityFood
All markets18.3%25.6%21.8%20.4%17.0%14.1%9.6%
Rural23.7%30.2%29.0%19.4%22.7%17.0%12.9%
Low density17.3%22.4%19.7%21.1%16.8%14.2%9.9%
High density14.6%18.3%17.8%20.4%13.5%11.4%7.1%
Very high density12.5%22.4%12.5%11.3%11.9%11.0%7.5%

Agreement is highest in rural markets and lowest in very-high-density markets overall. Retail stays higher than food at every density. Percent of cases where at least three engines chose the same top business.

The next table uses the same rows and categories. It counts the different businesses named across all four lists.

Average Distinct Businesses Named Across Four EnginesYext Research · Fig 4 · February to August 2026
Market densityOverallRetailFinancialServicesHealthcareHospitalityFood
All markets23181727232730
Rural21171629212525
Low density24181727242730
High density25191827242832
Very high density25172028242837

Food reaches 37 different businesses in very-high-density markets, where agreement is 7.5 percent. Category differences show pool size is one part of the pattern. Average unique business names across the four returned lists.

Finding 03

Each engine cites a different mix of pages

Gemini puts the largest share on brand sites. OpenAI puts the largest share on directories. Anthropic cites review sites far more than the other three. Perplexity is the most even across brand sites and directories. These shares describe sources named in answers, not every source or signal the engines may use.

Citation Mix by EngineYext Research · Fig 5 · February to August 2026
Gemini
Anthropic
Perplexity
OpenAI
First-party sites
Local websites
Directories and aggregators
Industry and government
Review platforms
Social, news, and forums
EngineFirst-partyLocalDirectoriesIndustryReviewsSocial
Gemini41.9%11.9%28.8%12.7%1.7%2.9%
Anthropic33.1%8.2%26.0%10.5%20.5%1.7%
Perplexity31.6%6.4%32.5%16.6%9.4%3.6%
OpenAI26.9%8.1%40.9%20.1%1.9%2.1%

No single page type carries the same share across all four engines. Reported share values by engine and citation class. Totals vary by one tenth of a point because of rounding.

Finding 04

Consideration and ranking reward different work

Clear location data is associated with being named. Reviews and ongoing activity help once a business is in the set. Posts, photos, responses, and site structure can support both stages.

Profile Signals Associated With Being NamedYext Research · Fig 6 · February to August 2026
Location pages
2.9×
Cover photo
2.8×
Business description
2.3×
Claimed profile
2.3×
Schema markup
2.1×
Recent posts
1.8×
Ten or more attributes
1.5×
Largest reported lever by category group
Retail and FoodLocation pages and schemaUp to 3.9×
Financial and HealthcareClaimed and complete profilesAbout 3×
ServicesRecent posts2.8×
The study reports Retail with Food and Financial with Healthcare in these category summaries.

The overall and category results support the same pattern. Clear location data helps a brand enter the set, while fresh activity supports its position. Relative lift values from matched profiles.

Rating still shapes the order inside a returned list. It works as one signal among several, not a universal rule.

Ratings of the Top Business in Each ListYext Research · Fig 7 · February to August 2026
4.8
Median star rating of the top pick
52%
Top picks rated 4.8 or higher
37%
Top picks rated exactly 5.0
11%
Top picks rated below 4.0

A high rating is common at the top, yet the highest-rated business in a returned list ranks first only 40 percent of the time. Top-pick rating measures from the matched profile analysis.

Engines can value ratings and still disagree because each engine ranks a different candidate set.

What the study can tell us. The study is not claiming that one field alone causes selection. It shows which businesses appear more often and the profile traits attached to top picks.
Finding 05

Consensus profiles show depth across many signals

Unanimous top picks are tied to a broad web presence. Their own website appears among cited pages in 91 percent of cases. Key directories also appear more often when engines agree.

Pages Associated With Unanimous Top PicksYext Research · Fig 8 · February to August 2026
91%

of unanimous top picks have their own website among the cited pages

Waze
2.6×
Chamber of Commerce
1.8×
Carfax for auto
1.8×
MapQuest
1.6×
GasBuddy for fuel
1.6×

The ratios compare how often each directory appears in unanimous answers with split answers. Own-site share and citation-frequency ratios from the consensus analysis.

The matched profiles show the profile gaps behind that web presence.

Profile Signals for Unanimous, Majority, and Typical BusinessesYext Research · Fig 9 · February to August 2026
Profile signalUnanimousMajorityTypical field
Median reviews56853119
New reviews per month12.210.41.9
Posts in the past year13.115.56.0
Photos18725888
Reviews answered62%55%33%
Local-business schema56%48%30%
Profile completeness95%93%80%
Average star rating4.24.23.7

Review depth and recent activity create the largest visible gaps. Star rating moves less than review count, responses, posts, photos, and schema. 15,472 unanimous matched profiles and a typical field of 6.6 million profiles. The majority count was not reported.

What you can do

Build for consideration, then keep earning rank

01

Make every location legible

Publish complete location pages, claim the profile, add a clear description, and use local-business schema.

02

Prioritize the category sources engines cite

Keep broad directory coverage complete, then focus on authoritative sources for each category.

03

Keep proof fresh

Build review depth, answer reviews, add photos, and post often enough that each location looks active.

A local scan can come later. Search your category in several engines and record which businesses each one considers.

Future research

The next tests should show the missing counts

  • Publish the case count behind each category and density cell, and define each density band.
  • Report citation counts, source-class rules, model versions, and the collection date for each engine.
  • Show the lift model, comparison group, controls, and confidence range for every profile signal.
  • Break the lift and benchmark tables out by Retail, Financial, Services, Healthcare, Hospitality, and Food.
  • Track the same cases over time. Show how pools and agreement change after model updates.
Common questions

Questions readers ask

How often do four engines recommend the same local business+
They chose the same top business in 4 percent of 491,972 shared local query-market cases. Four different businesses took the top spot in 48 percent.
Why do the engines disagree+
Each engine starts with a different set of businesses. It also cites a different mix of brand sites, local pages, directories, review sites, and public pages.
Does a larger market always reduce agreement+
Agreement often falls as the pool grows. Some categories break the trend, and clear gaps remain at each density.
Do ratings decide which business ranks first+
Ratings help, but they do not decide every list. The highest-rated business in a returned set ranks first 40 percent of the time.
Which profile fields are linked with being named+
Location pages, a cover photo, a description, a claimed profile, schema, recent posts, and complete fields all appear more often when a business is named.
Methodology

How the study was measured

The panel
3,569 distinct local keywords were tested from February through August 2026. The broad run covered 2.05 million local questions. The common comparison includes 491,972 query-market cases asked of all four engines. Cases with fewer than four engines were excluded from the consensus comparison.
The prompt
The core panel used unbranded local recommendation prompts in the form “What are the top 10 [category] near [neighborhood]?” The same prompt and place were tested across all four engines.
The engines
Google Gemini, OpenAI, Perplexity, and Anthropic were included. The study treated the first-ranked business as the top choice.
The market field
The analysis reports 124,820 market observations per month. Results are grouped into Rural, Low density, High density, and Very high density markets.
The categories
Retail, Financial, Services, Healthcare, Hospitality, and Food are reported separately in the market tables.
Companion local search
A traditional Google local search estimated the broader local field and matched businesses named in AI answers to public profile attributes. Name and place resolved variations in how the same business appeared across engines.
Agreement
Unanimity means all four engines ranked the same business first. The heatmap measures cases where at least three engines ranked the same business first.
Profile analysis
Ratings, reviews, review responses, posts, photos, schema, profile completeness, descriptions, attributes, and location pages were evaluated for matched profiles.
Benchmark cohorts
The unanimous profile table uses 15,472 matched profiles. The typical field contains 6.6 million profiles. Query-level agreement and profile-level benchmarks use different analysis grains.
Yext Research · Four AIs, one questionSeptember 2026

Get the latest from Yext Research

See what's changing in search, grounded in real user behavior.

Yext will process your personal data as described in Yext’s Privacy Policy.