[VELIU· LUCE](https://luce.veliu.com/index.html)
how AI engines recommend brands
PILOT · W30 Search / (Search brands, categories and engines)
Board ▾
Board [Overview](https://luce.veliu.com/index.html) [Running shoes](https://luce.veliu.com/c/running-shoes.html) [Wireless earbuds](https://luce.veliu.com/c/wireless-earbuds.html)
[Coffee machines](https://luce.veliu.com/answers.html#coffee-machines) measuring
[Robot vacuums](https://luce.veliu.com/answers.html#robot-vacuums) measuring
[Air fryers](https://luce.veliu.com/answers.html#air-fryers) measuring
[All brands](https://luce.veliu.com/brands.html) [Real answers](https://luce.veliu.com/answers.html)
Engines [ChatGPT](https://luce.veliu.com/e/chatgpt-web.html) [ChatGPT API](https://luce.veliu.com/e/chatgpt-api.html) [Gemini](https://luce.veliu.com/e/gemini.html) [Perplexity](https://luce.veliu.com/e/perplexity.html)
Research [Coverage](https://luce.veliu.com/coverage.html) [Methodology](https://luce.veliu.com/methodology.html) [Sources](https://luce.veliu.com/sources.html) [Glossary](https://luce.veliu.com/glossary.html) [Tools](https://luce.veliu.com/tools) (primary)
en-US · grammar luce-live-v0 Dark (Current theme: dark) (wave luce-live-w30 · grammar luce-live-v0 · generated 2026-07-15 19:49:02 UTC)
**PILOT · W30** real engine answers · small pilot wave · wide intervals by design Synthetic probes · not real user sessions · this wave 100% [L3](https://luce.veliu.com/glossary.html#provenance-tier) · answers [L1](https://luce.veliu.com/glossary.html#provenance-tier) elicited
Running shoes▾
[All categories](https://luce.veliu.com/index.html) [Running shoes](https://luce.veliu.com/c/running-shoes.html) [Wireless earbuds](https://luce.veliu.com/c/wireless-earbuds.html)
·
All engines▾
[All engines](https://luce.veliu.com/index.html) [ChatGPT](https://luce.veliu.com/e/chatgpt-web.html) [ChatGPT API](https://luce.veliu.com/e/chatgpt-api.html) [Gemini](https://luce.veliu.com/e/gemini.html) [Perplexity](https://luce.veliu.com/e/perplexity.html)
· en-US · LUCE-LIVE-W30 · measured from 15 Jul 2026 · 60 days ago (what you are viewing)
category
# Running shoes
Which running shoes do ChatGPT, ChatGPT API, Gemini and Perplexity put forward when a shopper names no brand? Across **30** questions from the published grammar, they do not agree on who to recommend: ChatGPT leads with ASICS, ChatGPT API ties ASICS and HOKA, Gemini ties Brooks and Saucony, Perplexity leads with ASICS.
Road running shoes across daily trainers and race day.
AI surfaces **4**
Brands **8**
[VELIU· LUCE](https://luce.veliu.com/index.html) **PILOT · W30**
the same prompts, two surfaces
## ChatGPT's app and its API seat the same brands on different shelves.
Divergence Index measuring **50%** 95% CI 0-75%
Named on both
8 brands
Agree at the head
ASICS and HOKA
Split at the shelf
Brooks and Nike
On one surface only
none this wave
The index is the distance between these two top shelves, on a 0 to 100% scale: 0% when the same brands sit on both, 100% when the shelves share nobody. At n=30 the index takes few distinct values, so a wide interval follows from the sample. Its interval is a bootstrap over the prompt clusters both surfaces answered. A resample where a surface seats no brand has no index, and those resamples are left out of the interval.
Consumer interface ChatGPT web, one real answer
ChatGPT en-US a recreation from the real answer
best running shoes for beginners 2026
If you're just getting into running, prioritize comfort, fit, and durability over the lightest or fastest shoe. Most beginners do best with a neutral daily trainer unless they know they need extra stability.
Best overall beginner shoe
‹ (Previous product)1 of 7 › (Next product)
- Brooks Ghost 17 **$109.97** DICK’S Sporting Goods
- HOKA Clifton 10 **$123.99** DICK’S Sporting Goods
- ASICS GEL-CUMULUS 28 **$144.99** DICK’S Sporting Goods
- Nike Pegasus 42 **$144.99** DICK’S Sporting Goods
- Brooks Adrenaline GTS 25 **$149.99** DICK’S Sporting Goods
- B photo not available Brooks Trace 4 **$99.99** DICK’S Sporting Goods
- N photo not available Nike Revolution 8 **$60.97** Nike (products ChatGPT put forward)
Show the full reply
If you're just getting into running, prioritize comfort, fit, and durability over the lightest or fastest shoe. Most beginners do best with a neutral daily trainer unless they know they need extra stability.
Best overall beginner shoe
Brooks Ghost 17
$109.97
•
DICK’S Sporting Goods
The Brooks Ghost line remains one of the most consistently recommended options for new runners because it strikes an excellent balance of cushioning, stability, and versatility. It's comfortable for run/walk programs, easy runs, and even daily walking. Multiple 2026 guides continue to rank it as a top beginner choice.
Runner's World
+2
Runner's World
+2
Other excellent beginner options
HOKA Clifton 10
$123.99 · DICK’S Sporting Goods
A lightweight, highly cushioned shoe that's ideal if you want softer landings without an overly bulky feel. Great for building mileage gradually.
The Run Testers
ASICS GEL-CUMULUS 28
$144.99 · DICK’S Sporting Goods
A dependable neutral trainer with balanced cushioning that works well for beginners who want a smooth ride for everyday training.
YouTube
+1
Nike Pegasus 42
$144.99 · DICK’S Sporting Goods
A versatile all-rounder that's responsive enough to grow with you as your pace improves while remaining comfortable for everyday runs.
YouTube
Brooks Adrenaline GTS 25
$149.99 · DICK’S Sporting Goods
Choose this if you know you overpronate (your foot rolls inward significantly) or you've previously been advised to use a stability shoe.
shoestation.com
+1
If you're on a budget
Brooks Trace 4
$99.99 · DICK’S Sporting Goods
A solid entry-level daily trainer that offers many of the Ghost's beginner-friendly characteristics at a lower price.
Or, if you're looking for an inexpensive first pair:
Nike Revolution 8
$60.97 · Nike
Suitable for casual running and run/walk programs if you're just starting out.
Quick buying tips
Most beginners: Choose a neutral shoe (Ghost, Clifton, Pegasus, GEL-CUMULUS).
Need extra support: Look at stability models like the Brooks Adrenaline GTS or Nike Structure.
Size: Running shoes often fit best with about a thumb's width of space in front of your longest toe.
Replace them: Expect roughly 300–500 miles (480–800 km) of running before cushioning noticeably degrades.
If you're 18–35, starting with 2–4 runs per week, the Brooks Ghost 17 or HOKA Clifton 10 are hard to beat as first running shoes in 2026.
Sources runnersworld.com theruntesters.com youtube.com shoestation.com
Developer API ChatGPT API, 30 prompts, measuring
ASICS **83%** 67-97
HOKA **83%** 70-97
Brooks **67%** 47-83 on the UI top shelf
Saucony **63%** 47-80
New Balance **57%** 40-73
Nike **53%** 37-70 on the UI top shelf
Adidas **23%** 10-40
On Running **7%** 0-17
Both cells hold 30 prompts, still measuring toward the precision gate, so read the shelves as the signal and the exact rates as provisional. (the Divergence Index: the consumer interface beside the API)
luce-live-w30 · measured from 15 Jul 2026 · en-US · ChatGPT web app · ChatGPT API L1 elicited · Synthetic probes · not real user sessions · this wave 100% L3 · n = 30 prompt clusters per cell probe-design mention rate over Luce grammar luce-live-v0; not demand-weighted Published by Veliu Research Lab. Veliu sells services to brands measured here. [https://luce.veliu.com/c/running-shoes#diptych](https://luce.veliu.com/c/running-shoes#diptych)
[Frame for screenshot](https://luce.veliu.com/c/running-shoes.html?card=diptych#diptych) (Frame for screenshot: diptych)
01
## Every brand, every engine
Read across a row to see where the engines disagree.
estimand: probe-design mention rate over Luce grammar luce-live-v0, rank-range leagues only; not demand-weighted · 30 prompts per cell (the exact quantity published on this surface)
SoVGapPrecision (board lens) All cells shown. 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. No cell diverges beyond its intervals this wave. Dashed cells carry a low precision tag: measured, with intervals too wide to rank this wave. Every cell stays readable.
[VELIU· LUCE](https://luce.veliu.com/index.html) **PILOT · W30**
One measurement per engine. Rows ordered by ChatGPT.
| Brand | ChatGPT web app mention rate · 95% CI | ChatGPT API mention rate · 95% CI | Gemini mention rate · 95% CI | Perplexity mention rate · 95% CI |
| --- | --- | --- | --- | --- |
| Gap: no cell diverges beyond its intervals this wave |
| [ASICS](https://luce.veliu.com/b/asics.html) | [**83%** 70-97](https://luce.veliu.com/answers.html) (ASICS on ChatGPT · 83% (95% CI 70-97%) · n = 30 prompts · L1 elicited) | [**83%** 67-97](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (ASICS on ChatGPT API · 83% (95% CI 67-97%) · n = 30 prompts · L1 elicited) | [**83%** 70-97](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (ASICS on Gemini · 83% (95% CI 70-97%) · n = 30 prompts · L1 elicited) | [**73%** 57-87](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (ASICS on Perplexity · 73% (95% CI 57-87%) · n = 30 prompts · L1 elicited) |
| [HOKA](https://luce.veliu.com/b/hoka.html) | [**80%** 67-93](https://luce.veliu.com/answers.html) (HOKA on ChatGPT · 80% (95% CI 67-93%) · n = 30 prompts · L1 elicited) | [**83%** 70-97](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (HOKA on ChatGPT API · 83% (95% CI 70-97%) · n = 30 prompts · L1 elicited) | [**87%** 73-97](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (HOKA on Gemini · 87% (95% CI 73-97%) · n = 30 prompts · L1 elicited) | [**70%** 53-87](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (HOKA on Perplexity · 70% (95% CI 53-87%) · n = 30 prompts · L1 elicited) |
| [Brooks](https://luce.veliu.com/b/brooks.html) | [**77%** 60-90](https://luce.veliu.com/answers.html) (Brooks on ChatGPT · 77% (95% CI 60-90%) · n = 30 prompts · L1 elicited) | [**67%** 47-83 low precision](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (Brooks on ChatGPT API · 67% (95% CI 47-83%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**90%** 77-100](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (Brooks on Gemini · 90% (95% CI 77-100%) · n = 30 prompts · L1 elicited) | [**70%** 53-83](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (Brooks on Perplexity · 70% (95% CI 53-83%) · n = 30 prompts · L1 elicited) |
| [Nike](https://luce.veliu.com/b/nike.html) | [**73%** 57-87](https://luce.veliu.com/answers.html) (Nike on ChatGPT · 73% (95% CI 57-87%) · n = 30 prompts · L1 elicited) | [**53%** 37-70 low precision](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (Nike on ChatGPT API · 53% (95% CI 37-70%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**73%** 57-90](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (Nike on Gemini · 73% (95% CI 57-90%) · n = 30 prompts · L1 elicited) | [**63%** 47-80 low precision](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (Nike on Perplexity · 63% (95% CI 47-80%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) |
| [Saucony](https://luce.veliu.com/b/saucony.html) | [**53%** 37-70 low precision](https://luce.veliu.com/answers.html) (Saucony on ChatGPT · 53% (95% CI 37-70%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**63%** 47-80 low precision](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (Saucony on ChatGPT API · 63% (95% CI 47-80%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**90%** 80-100](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (Saucony on Gemini · 90% (95% CI 80-100%) · n = 30 prompts · L1 elicited) | [**53%** 33-73 low precision](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (Saucony on Perplexity · 53% (95% CI 33-73%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) |
| [New Balance](https://luce.veliu.com/b/new-balance.html) | [**43%** 27-60 low precision](https://luce.veliu.com/answers.html) (New Balance on ChatGPT · 43% (95% CI 27-60%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**57%** 40-73 low precision](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (New Balance on ChatGPT API · 57% (95% CI 40-73%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**87%** 73-97](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (New Balance on Gemini · 87% (95% CI 73-97%) · n = 30 prompts · L1 elicited) | [**60%** 43-77 low precision](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (New Balance on Perplexity · 60% (95% CI 43-77%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) |
| [Adidas](https://luce.veliu.com/b/adidas.html) | [**23%** 10-40 low precision](https://luce.veliu.com/answers.html) (Adidas on ChatGPT · 23% (95% CI 10-40%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**23%** 10-40 low precision](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (Adidas on ChatGPT API · 23% (95% CI 10-40%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**67%** 50-83 low precision](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (Adidas on Gemini · 67% (95% CI 50-83%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**47%** 30-63 low precision](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (Adidas on Perplexity · 47% (95% CI 30-63%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) |
| [On Running](https://luce.veliu.com/b/on.html) | [**7%** 0-17 low precision](https://luce.veliu.com/answers.html) (On Running on ChatGPT · 7% (95% CI 0-17%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**7%** 0-17 low precision](https://luce.veliu.com/probes/running-shoes-en-us-chatgpt-api.html) (On Running on ChatGPT API · 7% (95% CI 0-17%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**23%** 10-40 low precision](https://luce.veliu.com/probes/running-shoes-en-us-gemini.html) (On Running on Gemini · 23% (95% CI 10-40%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) | [**17%** 3-30 low precision](https://luce.veliu.com/probes/running-shoes-en-us-perplexity.html) (On Running on Perplexity · 17% (95% CI 3-30%) · n = 30 prompts · L1 elicited · low precision, no rank this wave) |
luce-live-w30 · measured from 15 Jul 2026 · en-US · Running shoes · ChatGPT web app · ChatGPT API · Gemini · Perplexity L1 elicited · Synthetic probes · not real user sessions · this wave 100% L3 · n = 30 prompt clusters per cell 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, and its interval is drawn hatched. The bar under each rate is its 95% interval. probe-design mention rate over Luce grammar luce-live-v0; not demand-weighted Published by Veliu Research Lab. Veliu sells services to brands measured here. [https://luce.veliu.com/c/running-shoes#board-running-shoes](https://luce.veliu.com/c/running-shoes#board-running-shoes)
[Frame for screenshot](https://luce.veliu.com/c/running-shoes.html?card=board-running-shoes#board-running-shoes) (Frame for screenshot: board running shoes)
Behind these numbers
[ChatGPT 30 real answers →](https://luce.veliu.com/answers.html) (30 real answers behind ChatGPT)
Cite a cell from this board: [ChatGPT](https://luce.veliu.com/claim/luce-live-w30/running-shoes-chatgpt-web.html) · [ChatGPT API](https://luce.veliu.com/claim/luce-live-w30/running-shoes-chatgpt-api.html) · [Gemini](https://luce.veliu.com/claim/luce-live-w30/running-shoes-gemini.html) · [Perplexity](https://luce.veliu.com/claim/luce-live-w30/running-shoes-perplexity.html) . Each claim page states the interval, the sample and the wave with the number. Download the data behind a cell: [ChatGPT](https://luce.veliu.com/bundle/luce-live-w30/running-shoes-chatgpt-web.json) · [ChatGPT API](https://luce.veliu.com/bundle/luce-live-w30/running-shoes-chatgpt-api.json) · [Gemini](https://luce.veliu.com/bundle/luce-live-w30/running-shoes-gemini.json) · [Perplexity](https://luce.veliu.com/bundle/luce-live-w30/running-shoes-perplexity.json) . Each bundle carries the members with their intervals, the prompts, the estimator and the gate.
02
## Photo finish
ChatGPT web shows one real answer above; the three API surfaces race here.
estimand: probe-design leader credible-set read over Luce grammar luce-live-v0; not demand-weighted (the exact quantity published on this surface)
[VELIU· LUCE](https://luce.veliu.com/index.html) **PILOT · W30**
### ChatGPT API
Running shoes · 95% credible set: HOKA, ASICS
contested · no likely favorite (no brand holds a likely-favorite share of the top spot; the credible set is the honest answer)
Chance of the top spot · ± Monte Carlo SE
- HOKA 51% *±1.1*
- ASICS 48% *±1.1*
6 more brands in this cell hold under a one percent chance of the top spot.
luce-live-w30 · measured from 15 Jul 2026 · en-US · ChatGPT API L1 elicited · Synthetic probes · not real user sessions · this wave 100% L3 · n = 30 prompt clusters per cell probe-design leader credible-set read over Luce grammar luce-live-v0; not demand-weighted Published by Veliu Research Lab. Veliu sells services to brands measured here. [https://luce.veliu.com/c/running-shoes#photo-finish-running-shoes-chatgpt-api](https://luce.veliu.com/c/running-shoes#photo-finish-running-shoes-chatgpt-api)
[Frame for screenshot](https://luce.veliu.com/c/running-shoes.html?card=photo-finish-running-shoes-chatgpt-api#photo-finish-running-shoes-chatgpt-api) (Frame for screenshot: photo finish running shoes chatgpt api)
[VELIU· LUCE](https://luce.veliu.com/index.html) **PILOT · W30**
### Gemini
Running shoes · 95% credible set: Brooks, Saucony, HOKA, New Balance, ASICS
contested · no likely favorite (no brand holds a likely-favorite share of the top spot; the credible set is the honest answer)
Chance of the top spot · ± Monte Carlo SE
- Brooks 33% *±1.0*
- Saucony 33% *±1.0*
- HOKA 16% *±0.8*
- New Balance 12% *±0.7*
- ASICS 6% *±0.5*
3 more brands in this cell hold under a one percent chance of the top spot.
luce-live-w30 · measured from 15 Jul 2026 · en-US · Gemini L1 elicited · Synthetic probes · not real user sessions · this wave 100% L3 · n = 30 prompt clusters per cell probe-design leader credible-set read over Luce grammar luce-live-v0; not demand-weighted Published by Veliu Research Lab. Veliu sells services to brands measured here. [https://luce.veliu.com/c/running-shoes#photo-finish-running-shoes-gemini](https://luce.veliu.com/c/running-shoes#photo-finish-running-shoes-gemini)
[Frame for screenshot](https://luce.veliu.com/c/running-shoes.html?card=photo-finish-running-shoes-gemini#photo-finish-running-shoes-gemini) (Frame for screenshot: photo finish running shoes gemini)
[VELIU· LUCE](https://luce.veliu.com/index.html) **PILOT · W30**
### Perplexity
Running shoes · 95% credible set: ASICS, HOKA, Brooks, Nike
likely favorite · ASICS
Chance of the top spot · ± Monte Carlo SE
- ASICS 47% *±1.1*
- HOKA 22% *±0.9*
- Brooks 20% *±0.9*
- Nike 9% *±0.6*
- New Balance 2% *±0.3*
3 more brands in this cell hold under a one percent chance of the top spot.
luce-live-w30 · measured from 15 Jul 2026 · en-US · Perplexity L1 elicited · Synthetic probes · not real user sessions · this wave 100% L3 · n = 30 prompt clusters per cell probe-design leader credible-set read over Luce grammar luce-live-v0; not demand-weighted Published by Veliu Research Lab. Veliu sells services to brands measured here. [https://luce.veliu.com/c/running-shoes#photo-finish-running-shoes-perplexity](https://luce.veliu.com/c/running-shoes#photo-finish-running-shoes-perplexity)
[Frame for screenshot](https://luce.veliu.com/c/running-shoes.html?card=photo-finish-running-shoes-perplexity#photo-finish-running-shoes-perplexity) (Frame for screenshot: photo finish running shoes perplexity)
[VELIU· LUCE](https://luce.veliu.com/index.html) **PILOT · W30**
03
## Engines disagree
Excess divergence above the sampling noise floor.
Cross-engine divergence publishes when two cells clear the precision gate. None did this wave.
luce-live-w30 · measured from 15 Jul 2026 · en-US · ChatGPT web app · ChatGPT API · Gemini · Perplexity L1 elicited · Synthetic probes · not real user sessions · this wave 100% L3 Published by Veliu Research Lab. Veliu sells services to brands measured here. [https://luce.veliu.com/c/running-shoes#divergence](https://luce.veliu.com/c/running-shoes#divergence)
[Frame for screenshot](https://luce.veliu.com/c/running-shoes.html?card=divergence#divergence) (Frame for screenshot: divergence)
Rank ranges and leagues live on each engine's page: [ChatGPT](https://luce.veliu.com/e/chatgpt-web.html) · [ChatGPT API](https://luce.veliu.com/e/chatgpt-api.html) · [Gemini](https://luce.veliu.com/e/gemini.html) · [Perplexity](https://luce.veliu.com/e/perplexity.html)
Published by Veliu Research Lab. Veliu sells services to brands measured here.
Live pilot wave luce-live-w30. The method, the probe log and this wave's coverage are on the methodology page.