AIVO Win Rate

Example Full Test report

This is what a Full Test tells you

A real test, run on 28 September 2026: AI shopping agents on ChatGPT, Gemini, Perplexity worked through the same customer request 15 times. The business's name and website are hidden; everything else, including the competitors AI chose instead, is exactly as recorded.

Your AI shopping result · 15 runs · 3 assistants · 1 customer brief

1 of 15

AI picked A London seafood restaurant outright in 1 of 15 shopping runs.

You were found in 14 of 15 runs but lost most of them before the pick. J. Sheekey won 4 runs, more than you.

Found

14 / 15

Shortlisted

3 / 15

Picked outright

1 / 15

Win Rate range

1.5–25.1%

Confidence

Moderate: 5 runs per combination. Treat the rates as direction, not precision. 10+ runs gives firmer figures.

00 · Can AI agents reach you?

Agent access check

What a legitimate AI shopping agent could and couldn't read during this test. Blocks are recorded, never worked around.

Your page	Visits	Status
A London seafood restaurant	1	Readable
A London seafood restaurant	1	Readable

Other sites that turned the agents away (they then relied on other sources): thefork.co.uk (4), opentable.co.uk (4), opentable.com (2).

01 · The journey

Where you dropped out

Every run passes through the same stages. This is how many of the 15 reached each one with you still in it.

Foundagent came across you

93%

14 / 15

▼ lost 11 here · biggest drop

Shortlistedmade the agent's list

20%

3 / 15

Comparedin the final head-to-head

20%

3 / 15

▼ lost 2 here

Pickedthe agent's recommendation

1 / 15

02 · Every outcome

How all 15 runs ended

Not every run ends in one winner. We count every outcome.

Picked you	1
Picked a competitor	14
Picked nobody	0
Stopped without deciding	0
Didn't finish	0

03 · Who beat you

Who AI chose instead

The 14 runs a competitor won outright.

J. Sheekey

Applebee's

Behind

Baccalà

Applebee's Fish

Bentley's Oyster Bar & Grill

Named as the place or brand the agent chose; a park's operator or a listing site is folded into the place itself.

04 · By assistant

Each AI behaves differently

Assistant	Found	Picked	Winner most often
ChatGPT	5 / 5	0	Behind
Gemini	5 / 5	1	J. Sheekey
Perplexity	4 / 5	0	Applebee's

05 · By customer

Where AI thinks you fit

Customer brief	Found	Picked
Brief 1	14 / 15	1

Brief 1: “Looking for a good fish restaurant in London for 6 people on a Saturday might with a budget of up to GBP 150 per head”

06 · Why you lost

What the agents looked for and couldn't find

Taken from what the agents actually did: the pages they opened, what they searched for, and what they couldn't confirm. Observed means it happened in the recorded runs. Our read is our interpretation.

1 · ChatGPT and Perplexity always picked rivals with clearer facts

ObservedIn every ChatGPT and Perplexity run, the final pick was a rival (Behind, Applebee's, Baccalà, Bentley's) chosen because it had explicit, verifiable Saturday hours, six-person booking policy, and per-person pricing. A London seafood restaurant is never named as the runner-up reasoning in these excerpts.

Evidence: 8 rival picks · Facts

FixPublish a clear Saturday booking page for six, with set menu or a la carte price-per-head, so agents can verify budget fit directly. · web team

2 · Discovery is not the problem; verification is

Our readA London seafood restaurant was found in nearly all runs (ChatGPT 5/5, Perplexity 4/5, Gemini 5/5), so agents do see it. The gap is at shortlisting and picking, where rivals had explicit facts (price, hours, group booking) A London seafood restaurant pages did not clearly surface here.

Evidence: 2 rival picks, 1 run that picked you · Facts

FixAdd structured, explicit Saturday dinner details (hours, six-person booking, price range) to key pages so agents can confirm fit without inferring. · web team

3 · Gemini often shortlists A London seafood restaurant but fears budget overrun

ObservedGemini repeatedly considered A London seafood restaurant a top London seafood option but twice ruled it out in favour of J. Sheekey, warning that wine and service could push A London seafood restaurant past the £150 per head ceiling. This shows the business is competitive but seen as price-risky versus rivals.

Evidence: 2 rival picks · Competition

FixPublish transparent per-person cost examples (food, wine, service) so agents can confirm it stays within stated budgets. · content

4 · Gemini did pick A London seafood restaurant once with a generous budget framing

ObservedIn one run, Gemini picked A London seafood restaurant for a Saturday group dinner, praising its atmosphere and seafood menu as ideal for a big-budget night out. This shows the offer works when budget isn't framed as tight.

Evidence: 1 run that picked you · Competition

FixHighlight atmosphere and signature dishes prominently for higher-budget, special-occasion queries to reinforce this winning angle. · positioning

These are the decision points we saw in this test. Fixing them makes a win more likely but doesn't guarantee one. Rerun the same test afterwards to see what changed.

07 · The 1 run that never found you

What the agents searched for instead

Agent searched	Times
“London fish seafood restaurants Saturday dinner six people menu prices”	1
“site:thefork.co.uk London seafood restaurant Saturday dinner menu £ per person six”	1

08 · Replay a run

ChatGPT · Brief 1 lost to Applebee's

01Search“best seafood restaurants London menus prices fish Saturday dinner”

02Search“London fish restaurant private group six dinner menu prices”

03Search“site:theoystermen.com London menu booking seafood restaurant”

04Openoystermen.co.uk/foodmenu

05Openapplebeesfish.com/

06Openthesavoylondon.com/events-and-celebrations/the-river-restaurant-privat

07OpenA London seafood restaurant-restaurant.com/private-dining/

08Search“site:applebeesfish.com "£" "Food menu"”

09Openapplebeesfish.com/s/AF_Food-menu_Template_March2.pdf

Want this for your business?

Your Win Rate, where you drop out, which competitors AI picks instead, and what to fix. Pay per test, about US$45 for a first test, results in about 15 minutes.

Set up your Full Test →