Report
Mortgage brokers
Collected
24 Jul 2026
Market
Sydney, Australia
Assistants
ChatGPT · Perplexity · Gemini · Claude
Report · mortgage brokers · Sydney

We asked four AIs for Sydney’s best mortgage broker. Twice, ChatGPT named nobody.

On 24 July 2026 we put two buying questions to four AI assistants, four times each. The strangest result wasn’t who got named. It was how often nobody did.

The questions were “best mortgage broker in Sydney” and a first-home-buyer version for Bondi. 32 answers, one sitting.

The stability band, in one breath

Ask an AI the same question four times and the answers shift. The band is that range, and a change only counts as movement once it clears it.The method in full →

Half a shortlist, half a shrug.

Asked “Best mortgage broker in Sydney – who do you recommend?” four times in one sitting, ChatGPT named nobody, then 17 businesses, then nobody again, then 11. The empty answers weren’t errors.

fig. 1 · ChatGPT · businesses named per ask
0
ask 1
17
ask 2
0
ask 3
11
ask 4
best mortgage broker in Sydney · stability-mb v1 · Sydney 24 Jul 2026 · two of four asks returned no recommendation at all

download · png · svg

If your customers ask on the wrong try, no one gets recommended, including you. The physio study never returned an empty answer, so this trade behaves differently.

fig. 2 · how much each AI agrees with itself
0.00.51.0.22.44.50.54.341.00.80agreed just .14ChatGPT · near BondiChatGPTPerplexityGeminiClaude
best in Sydneynear Bondithe story reading

ChatGPT agreed just .14 – near Bondi.

ChatGPT
.22
.14
Perplexity
.44
.50
Gemini
.54
.34
Claude
1.00
.80
best in Sydneynear Bondi

0 = never the same answer · 1 = identical every time

The grey is the noise; the lume is the one reading the data will stand behind.

agreement with itself · 0 (never) to 1 (identical) · stability-mb v1 · Sydney 24 Jul 2026 · ChatGPT’s Sydney score includes its two empty answers – both counts in the dataset

download · png · svg

1the setup

What we did

Two buying questions: “best mortgage broker in Sydney”, and a first-home-buyer version anchored to Bondi. Four assistants, four times each, one sitting. 32 answers, asked the way a customer would ask.

We count businesses, not strings, and named branches stay apart from parent brands. The methodology covers what counts as one.

97 businesses turned up across 32 answers, and half were named once. The grid below is what each assistant returned, ask by ask.

fig. 3 · best in Sydney
assistantnames per answerbusinesses namednamed onceagreementnamed in all four
ChatGPT0 · 17 · 0 · 112114·67%0.22 / 0.33†– twice named nobody
Perplexity5 · 5 · 5 · 383·38%0.44Shore Financial
Gemini8 · 12 · 11 · 11176·35%0.54AFMS Group · Natloans · Shore Financial · Soren Financial · Villa Finance Group
Claude4 · 4 · 4 · 440·0%1.00Eden Emerald Mortgages · Get a Better Rate · Home Loan Experts · Soren Financial
agreement · 0 (never) to 1 (identical) · stability-mb v1 · Sydney 24 Jul 2026 · entity extraction v2.1 · both counts in the dataset
† ChatGPT twice named nobody; its score shows with and without those empty answers.

On the suburb-level question the lists were shorter, and ChatGPT held nothing at all across its four answers.

fig. 4 · near Bondi
assistantnames per answerbusinesses namednamed onceagreementnamed in all four
ChatGPT6 · 5 · 8 · 82015·75%0.14none
Perplexity9 · 4 · 6 · 8125·42%0.50Aussie Bondi Junction · Loan Market Unlimited · Mortgage Choice Bondi
Gemini1 · 5 · 4 · 8106·60%0.34Bondi Broker
Claude4 · 4 · 4 · 451·20%0.80Borro · Brampton Finance · Eventus Financial
agreement · 0 (never) to 1 (identical) · stability-mb v1 · Sydney 24 Jul 2026 · entity extraction v2.1 · both counts in the dataset
2the count

Half were named once, never again

Same city, same questions, asked the same way. Mortgage broking returned more businesses than physiotherapy, and more of them named once.

97
businesses named across 32 answers
50
named once and never again
17
held across all four answers

Claude did the opposite: the same four names, four times out of four. It was the steadiest and the narrowest answer in the study.

Set the two trades side by side and the churn is worse where the money is bigger.

fig. 5 · same questions, one trade over
same city, same weeksbusinesses namednamed onceheld all four
Physiotherapists853617
Mortgage brokers975017
entity extraction v2.1 · physiotherapists 7 Jul 2026 · mortgage brokers 24 Jul 2026
3the survivors

Who held across four answers

Seventeen businesses were named every time an assistant answered its question, and we checked each against a real brokerage before printing it. Shore Financial and Soren Financial held for two different assistants each.

One name deserves a second look. Natloans is a Melbourne brokerage, named by Gemini in all four answers to a question about Sydney. Being recommended is not the same as being local.

None of this is a ranking. Whether a name appears or disappears says something about the assistant giving the answer, not about the broker.

4the implication

Why this matters for measuring AI visibility

If two of four asks can return nobody at all, a single screenshot of an AI answer is worth even less than usual. A ranking published without a range, or without the empty answers counted, is noise dressed as signal.

This is why the methodology attaches a band and a date to every reading, and why The Southlume Index publishes rates with bands rather than bare ranks.

The assistant that names the most businesses agrees with itself the least.

5caveats

Open questions

One study is one snapshot. But the same thing keeps showing up: the physio study found this shuffle too, in a different trade.

We’re calling that a tendency, not a rule, until many more industries are measured.

on the recordquestion set stability-mb v1 · mortgage brokers · Sydney 24 Jul 2026 · 2 questions × 4 assistants × 4 asks, one sitting · entity extraction v2.1 · named branches kept apart from parent brands · survivor names verified against live businesses before publication · both counts published in the dataset.

The Southlume Index is measuring these categories now.

notify me · edition 1 →see the methodology →

Prompt checks are a sample; referral analytics are the ground truth of actual AI-driven visibility. A zero here is ‘not found on these prompts’, never ‘invisible’.