LIVE PILOTreal engine answers · small pilot wave · wide intervals by designSynthetic probes · not real user sessions · this wave 100% L3 · answers L1 eliciteden-US · luce-live-w28

Veliu Research Lab

Three AIs.
No single winner for running shoes.

Luce asked ChatGPT, Gemini and Perplexity the same 30 unbranded shopper questions about running shoes, and they do not agree on who to recommend: ChatGPT ties asics and hoka, Gemini leads with brooks, Perplexity leads with asics.

Engine calls180
Engines3
Categories2
Brands15
Prompts a cell30

estimand: probe-design mention rate over Luce grammar v0.1-pilot, rank-range leagues only; not demand-weighted

Gold marks the top rate on that engine, and every brand tied with it. Grey marks a brand measured too imprecisely to rank this wave. The bar under each rate is its 95% interval.

01

Running shoes

One column per engine, never combined. Rows ordered by ChatGPT.
BrandChatGPTmention rate · 95% CIGeminimention rate · 95% CIPerplexitymention rate · 95% CI
asics80%63-9380%67-9380%67-93
hoka80%67-9377%63-9070%53-87
brooks73%57-8787%73-9770%53-87
new-balance60%43-7777%60-9063%47-80
nike57%40-7367%50-8370%53-87
saucony53%33-7077%60-9057%40-73
adidas30%13-4760%43-7757%40-73
on7%0-1737%20-5313%3-27
02

Wireless earbuds

One column per engine, never combined. Rows ordered by ChatGPT.
BrandChatGPTmention rate · 95% CIGeminimention rate · 95% CIPerplexitymention rate · 95% CI
sony73%57-8780%67-9370%53-87
apple-airpods67%50-8350%33-6753%37-73
bose63%47-8063%43-8037%20-53
anker-soundcore47%30-6360%43-7757%40-73
jabra33%17-5027%13-4327%10-43
samsung-galaxy-buds27%10-4313%3-2720%7-37
sennheiser17%7-3017%3-303%0-10

1 market measured this wave. 17 markets and 10 sectors are queued, and nothing publishes until it is measured. How the board is built.