Free vs Plus
The ChatGPT app without a subscription against the paid plan, on the same prompts.
- The first search already names a brand in 30 of 94 Free answers and 78 of 100 Plus answers.
- Of the brands in the answer, 83% on Free and 47% on Plus were not in its first search, so search results had a chance to put them there. The rest were in its first search, named before any results.
- "Best …" articles make up 69% of Free's citations and 33% of Plus's; brands' own sites 11% and 36%.
- For the same prompt they agree on 49% of the brands they name between them.
Every prompt ends by asking ChatGPT to list the searches it ran. The app hides the text of some searches, mostly the second-layer fan-outs it runs while reasoning, so for the app's query numbers this self-report is the default: it is used when it contains every query seen in the stream (Free 93 of 100, Plus 100 of 100 answers), otherwise only what was seen counts. Where the self-report changes a number, the number without it is shown under it. Search steps, page reads, citations and brands always come from the stream.
How much it searches
Counted from search events, which both surfaces show even when the app hides the query text.
Seen: events in the app's stream or calls in the API response.
The first search
Does ChatGPT start from brands it already has in mind, or from an open search? The first search step decides it.
A step can hold several queries. It counts as naming a brand when at least one of them does. The step is taken from the stream on every surface. Round 1 of the app's self-report fills in only a first step whose text was hidden: that round also lists product lookups by name that ran in no visible step, so it would overstate how often the first search names a brand.
From memory to the answer
The first search runs before ChatGPT has seen any results, so the brands it names there come from what the model already knows. How many of them survive into the answer, and how much of the answer they make up?
Brands are matched loosely: “RAV4” in a query matches “Toyota RAV4 Hybrid” in the answer. Answers that did not search, or whose first search hid its text, are left out. On the app, a hidden first step is filled from round 1 of the self-report.
Search journeys
A journey is the searches of one answer in order. Two questions sort them: does the first search already name brands, and does ChatGPT search again once it has seen results?
Most common: never searches for a brand on Free (60% of answers), names brands, searches once on Plus (57%).
A second search is counted from the search steps in the stream, or from a later round of the self-report on the app. Brands are matched loosely, as above.
- 2 queries · List
- best online tire retailers tires
- best places to buy tires online US shipping installation warranty 2026
- 4 queries · List with brands, Brand check, Facts
- Michelin Defender2 225/65R17 Tire
- Continental TrueContact Tour 54 225/65R17
- best places to buy tires online Tire Rack Discount Tire SimpleTire Walmart Costco installation shipping 2026
- and 1 more
Query kinds
The mix of its queries: each slice is the share of its queries of that kind. Each prompt's answer page shows every query with its kind.
Most common: open list search on Free, brand check on Plus.
Kinds come from the classifier's query labels. On the app the mix includes the self-report, which also covers the steps whose text the app hid; the table gives the mix without it. Lookups the self-report puts in its first round but the stream shows in no step count under all searches only.
| Kind | Free | Plus |
|---|---|---|
| Topic search | 7% 16 5% without the self-report | 1% 5 1% without the self-report |
| Open list search | 55% 124 55% without the self-report | 10% 53 14% without the self-report |
| List search with its own picks | 10% 23 16% without the self-report | 12% 63 15% without the self-report |
| Brand check | 10% 23 2% without the self-report | 36% 194 11% without the self-report |
| Fact lookup | 8% 17 8% without the self-report | 26% 138 34% without the self-report |
| Comparison | 2% 5 3% without the self-report | 2% 12 4% without the self-report |
| Reviews and forums | 1% 2 2% without the self-report | 3% 18 6% without the self-report |
| Other: news, official rules, not labeled | 7% 15 10% without the self-report | 10% 54 16% without the self-report |
| Kind | Free | Plus |
|---|---|---|
| Topic search | 5% 6 5% without the self-report | 1% 2 1% without the self-report |
| Open list search | 55% 73 55% without the self-report | 14% 42 14% without the self-report |
| List search with its own picks | 16% 21 16% without the self-report | 15% 47 15% without the self-report |
| Brand check | 2% 2 2% without the self-report | 11% 33 11% without the self-report |
| Fact lookup | 8% 11 8% without the self-report | 34% 104 34% without the self-report |
| Comparison | 3% 4 3% without the self-report | 4% 12 4% without the self-report |
| Reviews and forums | 2% 2 2% without the self-report | 6% 17 6% without the self-report |
| Other: news, official rules, not labeled | 10% 13 10% without the self-report | 16% 48 16% without the self-report |
| Kind | Free | Plus |
|---|---|---|
| List search with its own picks | 0% 0 – without the self-report | 4% 5 – without the self-report |
| Brand check | 20% 2 – without the self-report | 60% 68 – without the self-report |
| Fact lookup | 60% 6 – without the self-report | 29% 33 – without the self-report |
| Reviews and forums | 0% 0 – without the self-report | 1% 1 – without the self-report |
| Other: news, official rules, not labeled | 20% 2 – without the self-report | 5% 6 – without the self-report |
What it searches for
Share of answers with at least one query of each type.
“Words” rows are read from the text of the query, so anyone can check them. “Classifier” rows come from the query labels. On the app the numbers include the self-report; the number without it follows where it differs.
Pages it reads
Opening a page means reading it beyond the title and snippet in the search results.
The last two rows read the overlap both ways: how much of what it cites it had read, and how much of what it read it cites.
The Free stream showed no page reads in this wave. That can mean ChatGPT worked from search results alone, or that the app does not show its reads; the data cannot tell the two apart.
What reaches the answer
What the reader gets: citations, links in the text, the sites behind them and the brands named.
For the same prompt, the two share 23% of their cited sites on average.
Ads
Ads shown in the answer, where the ad check ran.
What the web can move
How much of the answer is open to what search finds, rather than fixed by what the model already knows. Content cannot change the model's memory, but it can change what these searches return.
The rows below are the ways in, each a share that can be checked on the answer pages. Page types and site types come from the classifier's labels. Cited pages that are among the search results the app shows: Free 335 of 348, Plus 622 of 624.
Every prompt in detail
Each prompt with its searches, citations, links and brands on all three surfaces is on its category page.
Read with care
What these numbers can and cannot say.
- The prompts decide most of what these numbers can say. They are 100 commercial searches such as “best credit cards for travel” or “where to open a roth ira”, typed word for word as US searchers type them, in five categories. There are no comparison, advice or opinion prompts. Read every share as true for prompts like these, not for ChatGPT in general.
- One run per prompt and surface. ChatGPT does not answer the same way twice, so a single prompt can differ by chance; averages over many prompts are what to read.
- The surfaces run different models (Free: gpt-6; Plus: gpt-6-thinking). A difference between them is the surface and the model together.
- The app hides the query text of some search steps (Free 5%, Plus 19%). Query numbers for the app include ChatGPT's own list of its searches to fill that gap; a list the model wrote can miss or add a search.
- Search results are not compared: the API returns every result it got, the app only what it shows.