Skip to content
IndexesFor DMOs & tourism boardsAboutContact

AI Shortlist · Edition 1, 2027 travel year

West Virginia, USA in AI travel recommendations

US state · overall rank 160 of 233 · rank 43 among US state destinations

AI models put West Virginia, USA in their top 10 recommendations in 0.3% of answers, rank 160 overall. It does best when the question specifies how it's asked as underrated: 6.3%, +6.0 points against its overall score.

The score is the share of answers that recommend West Virginia, USA in their top 10, averaged model by model and then platform by platform, so each platform counts equally.

This destination in the other indexes: Source Control

By platform

PlatformScore
Claude0.0%
ChatGPT0.2%
Gemini0.8%
Grok0.0%

By model

ModelScore
Claude Opus 50.0%
Claude Sonnet 50.0%
Claude Haiku 4.50.0%
GPT-5.6 Terra0.0%
GPT-5.6 Luna0.4%
Gemini 3.8 Flash0.8%
Grok 4.60.0%

Web search and effort

West Virginia, USA · Edition 1, 2027 travel year

Unit: Shortlist score, percent of answers

West Virginia, USA with web search on and off, and at each model's lowest and normal effort setting.

Show as table
SettingSearch on / normal effortSearch off / lowest effort
Web search on vs off0.5%n/a
Normal vs lowest effort0.4%0.1%

The repeated baseline question never put this destination in its top 10, so it has no repeat figure.

By kind of question

How much higher or lower the score is on questions that ask for each option, in percentage points against the overall score. Outlined cells are below the overall score.

How it's asked

Unit: percentage points versus overall score
UnderratedWhere should I go?
Change+6.0−0.1

Trip length

Unit: percentage points versus overall score
Weekend
Change+0.7

Season

Unit: percentage points versus overall score
FallSpring
Change+0.4+0.1

Travel style

Unit: percentage points versus overall score
Adventure
Change−0.3

How the models wrote the name

NameMentions
New River Gorge3
Harpers Ferry1
New River Gorge National Park and Preserve1

West Virginia, USA

Most questions went to each model at each setting only once, and a model read the answers, so a reading can be wrong. The methodology has the details.

Loading mentions…

Request a destination scan

One destinationReal travel questionsSources you can inspect