Public sample · a real scan of a real market

Plumbers in Cincinnati, OH

Client: Anderson Hills Plumbing · report 4 · scan of August 16, 2026 · 30 answers
ScoredByAI
Anderson Hills Plumbing is shown as the example client for demonstration only; it is not a ScoredByAI customer and did not order this scan. All businesses, figures and sources below are real, measured on August 16, 2026.
Dominant
83%
90% CI 70 to 92% · n=30
Anderson Hills Plumbing was named or shown in 25 of the 30 answers ChatGPT gave to a Cincinnati customer asking for a plumber. The 10 businesses ChatGPT names most often come up in 70% of answers on average.
Invisiblenever named
Rareunder 10%
Weak10% to 39%
Solid40% to 64%
Dominant65% and up

How we grade: the band your client sits in is highlighted. Bands are read off the share of answers; the 90% intervals in the table below say how tight each share is, and never move a status by themselves.

Visibility + share of voice 83% +10Visibility: named in 25 of the 30 answers8.3% +1.9Share of voice: those same 25 of the market's 301 mentions, against an average of 6.9% for the 10 regularssee every reporthide

This clientAverage of the 10 regulars: the businesses ChatGPT names most often

gpt-5-5gpt-5-6 50% 0 Jul 30 Aug 3 Aug 8 Aug 16 68% 53% 79% 47% 81% 73% 70% 83% Jul 30 · report 1 53% Vis · 4.3% SoV 68% Vis · 5.5% SoV Aug 3 · report 2 47% Vis · 4.0% SoV 79% Vis · 6.8% SoV Aug 8 · report 3 73% Vis · 6.5% SoV 81% Vis · 7.2% SoV Aug 16 · report 4 83% Vis · 8.3% SoV 70% Vis · 6.9% SoV

Share of voice is not drawn as a second line: it moves with visibility. Point at a report to read its figures.

Avg position in places block 2.8 ↑6.1 of 6.9 cards shown per answersee every reporthide

This clientAverage of the 10 regulars: the businesses ChatGPT names most often

gpt-5-5gpt-5-6 1st 10th Jul 30 Aug 3 Aug 8 Aug 16 4.8 9.1 5.6 9.8 6.0 8.9 4.0 2.8 Jul 30 · report 1 9.1 · card in 8 of 30 Aug 3 · report 2 9.8 · card in 13 of 30 Aug 8 · report 3 8.9 · card in 19 of 30 Aug 16 · report 4 2.8 · card in 24 of 30

Point at a report to see how many of its answers showed this business as a card.

Click a metric to see every report. The shaded parts of each chart mark where OpenAI changed the engine under this market.

Your client's mentions in detail

In these 30 answers
Named in the written text25 of 30
Shown as a card in the places block24 of 30
Of those 24 cards, the listing behind them was:
a Yelp listing24 of 24

The rating shown beside the answer is the one on that Yelp listing: 3.4★ from 25 reviews. Whatever the Google profile says, it is not what they see here. Average card position 2.8 of 6.9 cards shown.

Full market table

Every business ChatGPT named or showed a card for in report 4, sorted by visibility. Your client's row is highlighted.

#BusinessVisibilityShare of voice Written answer · 90% CI Places block · 90% CI
1 Anderson Hills Plumbing (example client) 83% [70-92] 8.3%
25/30 · 83% [70-92]
24/30 · 80% [66-89]
2 Wake Plumbing 83% [70-92] 8.3%
25/30 · 83% [70-92]
0/30 · 0% [0-8]
3 Roto Rooter Plumbing & Water Cleanup 80% [66-89] 8.0%
24/30 · 80% [66-89]
24/30 · 80% [66-89]
4 Queen City Plumbing 80% [66-89] 8.0%
24/30 · 80% [66-89]
0/30 · 0% [0-8]
5 Ken Neyer Plumbing INC 77% [62-87] 7.6%
23/30 · 77% [62-87]
22/30 · 73% [59-84]
6 Plumb Tite Plumbing & Drains 73% [59-84] 7.3%
22/30 · 73% [59-84]
22/30 · 73% [59-84]
7 Mcguire Plumbing 63% [48-76] 6.3%
19/30 · 63% [48-76]
0/30 · 0% [0-8]
8 Herrmann Services 60% [45-73] 6.0%
18/30 · 60% [45-73]
18/30 · 60% [45-73]
9 Preston & Sons 50% [36-64] 5.0%
15/30 · 50% [36-64]
14/30 · 47% [33-61]
10 Blue Chip Plumbing 47% [33-61] 4.7%
14/30 · 47% [33-61]
14/30 · 47% [33-61]
11 Apollo Home 37% [24-52] 3.7%
11/30 · 37% [24-52]
11/30 · 37% [24-52]
12 Roberson Brothers Plumbing 37% [24-52] 3.7%
11/30 · 37% [24-52]
11/30 · 37% [24-52]
13 Schneller Knochelmann Plumbing Heating & Air Conditioning 37% [24-52] 3.7%
11/30 · 37% [24-52]
11/30 · 37% [24-52]
14 Halpin Plumbing 20% [11-34] 2.0%
6/30 · 20% [11-34]
6/30 · 20% [11-34]
15 Gardner Plumbing 20% [11-34] 2.0%
6/30 · 20% [11-34]
3/30 · 10% [4-23]
16 Trinity Plumbing and Water 20% [11-34] 2.0%
6/30 · 20% [11-34]
0/30 · 0% [0-8]
17 Narrow Path Plumbing 17% [8-30] 1.7%
5/30 · 17% [8-30]
0/30 · 0% [0-8]
18 Calla Plumbing 13% [6-27] 1.3%
4/30 · 13% [6-27]
4/30 · 13% [6-27]
19 Midwestern Plumbing 13% [6-27] 1.3%
4/30 · 13% [6-27]
4/30 · 13% [6-27]
20 Nieman Plumbing 13% [6-27] 1.3%
4/30 · 13% [6-27]
2/30 · 7% [2-18]
21 Chaney Services 10% [4-23] 1.0%
3/30 · 10% [4-23]
3/30 · 10% [4-23]
22 Jmw Plumbing & Fire Protection 10% [4-23] 1.0%
3/30 · 10% [4-23]
3/30 · 10% [4-23]
23 Tarvin Plumbing 10% [4-23] 1.0%
3/30 · 10% [4-23]
3/30 · 10% [4-23]
24 Elite Plumbing Services 10% [4-23] 1.0%
3/30 · 10% [4-23]
0/30 · 0% [0-8]
25 Safe Plumbing 10% [4-23] 1.0%
3/30 · 10% [4-23]
0/30 · 0% [0-8]
26 A Plumbing 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
27 Chase Brothers Plumbing 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
28 De Plumbing 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
29 Hofmeyer Plumbing 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
30 Jolly Heating Air Plumbing Electric 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
31 Mr Rooter Plumbing of Greater Cincinnati 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
32 Pembroke Plumbing 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
33 Service Experts Cincinnati 3% [1-14] 0.3%
1/30 · 3% [1-14]
1/30 · 3% [1-14]
34 Knochelmann Service Experts (no Google Maps match) 3% [1-14] 0.3%
1/30 · 3% [1-14]
0/30 · 0% [0-8]

Map card details

Ratings and review counts exactly as the cards displayed them. Cards counts the answers that showed a card for this business.

How to read this
Cards is how many of the 30 answers showed a card for this business. sl marks shortlist entries, cards ChatGPT prepared and decided not to show, so 8 · 2 sl reads as 8 answers with a card plus 2 more where a card was ready and held back. Avg pos is the average position in the places block when shown. Source is the directory a card was built from, with how many cards came from it. ChatGPT does not label it: we read it off secondary details on the card, so this is our reading rather than something ChatGPT stated. Shortlisted cards are never read this way, and a dash means the cards carried nothing we could read a source from.
BusinessAvg posReviewsCardsSource
Anderson Hills Plumbing (example client) 2.83.425 24 Yelp 24
Roto Rooter Plumbing & Water Cleanup 5.23.0248 24 · 1 sl Yelp 24
Ken Neyer Plumbing INC 3.44.033 22 Yelp 22
Plumb Tite Plumbing & Drains 3.04.9636 22 · 8 sl Google 13 · Yelp 9
Herrmann Services 5.33.018 18 Yelp 18
Preston & Sons 4.24.8175 14 · 14 sl Google 14
Blue Chip Plumbing 4.44.29 14 Yelp 14
Apollo Home 2.81.8223 11 · 2 sl Yelp 11
Roberson Brothers Plumbing 4.54.8185 11 · 17 sl Google 11
Schneller Knochelmann Plumbing Heating & Air Conditioning 4.83.242 11 Yelp 11
Halpin Plumbing 6.23.621 6 Yelp 6
Gardner Plumbing 4.05.053 3 Google 3
Calla Plumbing 5.84.8135 4 · 12 sl Google 4
Midwestern Plumbing 4.54.9331 4 · 26 sl Google 4
Nieman Plumbing 7.53.77 2 Yelp 2
Chaney Services 5.75.0221 3 · 26 sl Google 3
Jmw Plumbing & Fire Protection 3.75.0115 3 · 27 sl Google 3
Tarvin Plumbing 5.04.350 3 · 1 sl Yelp 3
A Plumbing 5.04.91075 1 · 29 sl Google 1
Chase Brothers Plumbing 5.04.9126 1 · 4 sl Google 1
De Plumbing 3.05.036 1 · 6 sl Google 1
Hofmeyer Plumbing 5.04.8147 1 Google 1
Jolly Heating Air Plumbing Electric 1.04.970 1 · 3 sl Google 1
Mr Rooter Plumbing of Greater Cincinnati 3.01.03 1 Yelp 1
Pembroke Plumbing 7.04.9191 1 · 8 sl Google 1
Service Experts Cincinnati 3.02.663 1 Yelp 1
Copper Pipe Plumbing Services INC 4.9140 5 sl
Dixon Plumbing & Service 5.0412 25 sl
Kings Plumbing 4.935 6 sl
Nobles Plumbing and Drain Cleaning Services LLC 5.069 3 sl
Salt Dog Plumbing LLC 5.0153 22 sl
Tj's Plumbing Installation and Repair 4.9126 4 sl

The market on a map

Every business ChatGPT built a card for in this report, at the coordinates ChatGPT itself sent with the card. Dot size = how many of the 30 answers named it.

How to read this
Coordinates come from the cards themselves, not from a directory lookup, so this is where ChatGPT believes each business sits. The street layer under the dots is served from this same domain, so the page still makes no request to anyone else.
your client the rest of the market, size = answers naming it Click the map to zoom with your scroll wheelScroll to zoom. Click outside the map when you are done

Pins are plotted from the coordinates ChatGPT returned in its own answers, not from a directory lookup. Street layer: Protomaps, OpenStreetMap data, served from this domain.

Sources behind the answers

Sites ChatGPT read before answering, by how many of the 30 answers cited them.

DomainAnswers citingShare
angi.com18 60%
homeadvisor.com18 60%
birdeye.com18 60%
yahoo.com17 57%
bestpickreports.com16 53%
consumeraffairs.com8 27%
serviceagent.ai7 23%
expertise.com7 23%
bestprosintown.com5 17%
seolium.com5 17%
recommended.app4 13%
threebestrated.com4 13%

Search queries the model ran

The searches ChatGPT actually fired before answering, with how many of the 30 answers fired each one.

best plumbers in Cincinnati Ohio reviews×9
best plumbers in Cincinnati Ohio×7
best plumbers Cincinnati Ohio reviews×5
top plumbers Cincinnati Ohio reviews×3
top plumbers in Cincinnati Ohio×1
best plumbers Cincinnati Ohio Roto-Rooter Apollo Home Plumb Tite×1
best plumbers Cincinnati Ohio Roto-Rooter Apollo Home Mr Rooter×1
top plumbers in Cincinnati Ohio reviews×1
best plumbers Cincinnati Ohio×1
best plumbers Cincinnati Ohio highly rated plumbers 2026×1
How this was measured
What an answer looks like
ONE CHATGPT ANSWER written text · the name appears here PLACES BLOCK EACH CARD IS BUILT FROM a Yelp or Google listing its rating and reviews come from there The highlighted card and the highlighted line of text are the same business.

A Yelp or Google listing builds most of the cards in this market, but they are not the only sources: other directories, and pages from the answer's own web search, build cards too. Whichever listing built a card is where its rating and review count come from.

Where we askedThe real ChatGPT web app, asked the way a customer in your city would ask it, as a signed out visitor. Not a developer API.
How many times30 independent answers, spread across natural phrasings a real customer would use. A single answer proves nothing, because the model gives a different one every time.
What counts as a mentionEach answer is read on 2 surfaces: the written text and the places carousel, the block of business cards ChatGPT shows beside its answer. An answer counts once if either happened.
How your status is setFrom the share of the 30 answers, against the five bands above. The 90% intervals say how tight that share is and never move a status by themselves.
Share of voiceThe client's mentions divided by all business mentions in the same scan, counted once per answer per business. 25 of 301 here.
How businesses are matchedBy map listing id, never by name text, so a business with a similar name in another town cannot be counted as this one.
Out of area Of the 207 map card mentions whose coordinates ChatGPT gave us, 0 (0%) are businesses more than 62 miles from the center of this market; those rows are tagged with the distance. This is noise in the model's own answers, not a measurement error.
What the charts compare againstThe 10 businesses ChatGPT names most often in this market, not every name it happened to mention. A market carries a long tail of names that come up once or twice, and averaging those in would flatter every business measured against them. The 10 are recomputed for every report, and a chain counts once, exactly as it does in the table above.
Measurement environmentEngine gpt-5-6 in all 30 answers, map block present in 30 of 30, 6.9 cards per answer, 10.0 businesses named per answer.
What the chat window does not showEvery one of these 30 answers was also read underneath the text: which directory built each card, which cards ChatGPT prepared and then held back (the shortlist), and what position each card sat at. Reading the answers by eye gives you the names and nothing else, which is why this view exists.
What this does not tell youNot how many people asked, and not what any one person saw. ChatGPT varies its answers by design and adapts to a person's own history, so these figures describe how often a business comes up for a stranger asking fresh, which is the only thing that can be measured the same way twice.
Report history
August 16, 2026 (this report)