collected

A Collected data story

What seven AI models tell you to read

We asked GPT, Claude, Gemini, Grok, Muse, DeepSeek and Mistral the same 100 questions about books, like "What should I read next?", "What are the best thrillers?" and "What books will make me laugh out loud?"

These are the books they recommended most. The bigger the cover, the more often it came up.

Each genre's recommendations are highly concentrated

We asked 7 models for 5 books in each of 20 genres and repeated each question 5 times, so 175 different books could have come up per genre. Yet the typical genre got just 18 unique books recommended across all models, ranging from 11 in true crime to 29 in dark romance. In 13 of the 20 genres, the same book appeared in every answer.

GenreDifferent booksMost recommended
True crime11
In Cold Blood
In Cold Blood34 of 34 answers
Self-help12
Atomic Habits
Atomic Habits35 of 35 answers
Science fiction13
Dune
Dune35 of 35 answers
Horror15
Dracula
Dracula35 of 35 answers
Thrillers15
Gone Girl
Gone Girl35 of 35 answers
Fantasy16
The Name of the Wind
The Name of the Wind30 of 35 answers
Historical fiction16
Wolf Hall
Wolf Hall35 of 35 answers
Memoirs16
Educated
Educated35 of 35 answers
Mystery16
The Hound of the Baskervilles
The Hound of the Baskervilles33 of 35 answers
Business18
Good to Great
Good to Great35 of 35 answers
Popular science18
The Selfish Gene
The Selfish Gene35 of 35 answers
Graphic novels20
Maus
Maus32 of 32 answers
Young adult20
The Hate U Give
The Hate U Give33 of 34 answers
History21
SPQR
SPQR31 of 35 answers
Romance22
Pride and Prejudice
Pride and Prejudice35 of 35 answers
Literary fiction24
Wolf Hall
Wolf Hall32 of 35 answers
Biography25
The Power Broker
The Power Broker33 of 35 answers
Cozy mysteries25
The Murder at the Vicarage
The Murder at the Vicarage31 of 33 answers
Poetry26
Leaves of Grass
Leaves of Grass33 of 33 answers
Dark romance29
Haunting Adeline
Haunting Adeline35 of 35 answers

A few answers came back empty, so some genres have fewer than 35.

Beach Read

"What are good beach reads?"

All seven models name a book called Beach Read.

We asked five times each, and it came up in 33 of 35 answers.

GPTClaudeGeminiGrokMuseDeepSeekMistral

Other questions get the same few books too

Asked what will make you laugh out loud, the models had 35 answers and room for 175 different books. They named just 13. The Hitchhiker's Guide to the Galaxy was in all 35 answers.

The Hitchhiker’s Guide to the Galaxy
What books will make me laugh out loud?The Hitchhiker’s Guide to the Galaxy
35 of 35 answers
The House in the Cerulean Sea
What's a cozy book for a rainy weekend?The House in the Cerulean Sea
All 7 models
To Kill a Mockingbird
What's a book everyone should read at least once?To Kill a Mockingbird
All 7 models

Asking again gets mostly the same books

When we asked a model the same question again, about 75% of the books it had already named came back.

The 72 books every model recommended

Pride and Prejudice; James; Gone Girl; Beloved; Project Hail Mary; And Then There Were None; The Haunting of Hill House; Educated; The Hunger Games; To Kill a Mockingbird; From Blood and Ash; The House in the Cerulean Sea; The Girl with the Dragon Tattoo; The Left Hand of Darkness; One Hundred Years of Solitude; Wolf Hall; The Book Thief; 1984; Never Let Me Go; The Hitchhiker’s Guide to the Galaxy; The Fault in Our Stars; Guns, Germs, and Steel; The Maze Runner; Middlemarch; Don Quixote; The Serpent and the Wings of Night; Persepolis; The Name of the Wind; The 7 Habits of Highly Effective People; Beach Read; Daisy Jones & The Six; In Cold Blood; The Giver; The Tainted Cup; Demon Copperhead; The Guernsey Literary and Potato Peel Pie Society; The Cruel Prince; Humankind; Dune; Atomic Habits; The Great Alone; The Glass Castle; The Girl on the Train; How to Train Your Dragon; Cribsheet; Divergent; If We Were Villains; Haunting Adeline; Me Talk Pretty One Day; It’s OK That You’re Not OK; A Little Life; Tiny Habits; The Power of Habit; Good to Great; The Lean Startup; Leaves of Grass; Ariel; The Hate U Give; The Shining; Dracula; Maus; Watchmen; Children of Time; The Woman in Black; The Turn of the Screw; Exciting Times; Neuromancer; The Stranger Beside Me; I'll Be Gone in the Dark; Cosmos; The Selfish Gene; The Hound of the Baskervilles

Colleen Hoover: 0. Several of the biggest names never come up

Colleen Hoover is the most popular author on Open Library among the books we track. In 1,405 answers, no model recommended her. James Patterson has more books on NYT bestseller lists than any other author we track, and he never came up at all.

The models mostly name well-known books. But 27 of the 50 most-logged books on Open Library never came up.

Most logged on Open Library

Atomic Habits
8 picks
The 48 Laws of Power
0 picks
It Ends with Us
0 picks
Rich Dad Poor Dad
0 picks
The Subtle Art of Not Giving a F*ck
1 pick
Harry Potter and the Sorcerer's Stone
1 pick
It Starts with Us
0 picks
Think and Grow Rich
0 picks
Twisted Love
0 picks
The Psychology of Money
2 picks
How to Win Friends and Influence People
8 picks
A Game of Thrones
5 picks

Most recommended by the models

Pride and Prejudice
33 picks
James
21 picks
Gone Girl
18 picks
Beloved
18 picks
Man’s Search for Meaning
18 picks
The Thursday Murder Club
17 picks
The Women
17 picks
Project Hail Mary
16 picks
And Then There Were None
16 picks
Sapiens
15 picks
The Haunting of Hill House
14 picks
Born a Crime
13 picks

Every book, plotted

Higher means the models recommend it more. Further right means more logged on Open Library. The red dots are popular books no model recommended. Hover or tap any dot.

Bestseller regulars, and how often they came up

The bar is how many books they've had on NYT lists. The number is how many times the models recommended them.

James Patterson 167
0
Nora Roberts 99
0
Debbie Macomber 71
0
Danielle Steel 64
0
Christine Feehan 58
0
Clive Cussler 53
2
David Baldacci 42
0
Janet Evanovich 39
0
Lynsay Sands 34
0
Stephen King 33
47
Robyn Carr 31
0
Karen Kingsbury 30
0
John Sandford 29
0
Michael Connelly 26
1
Sandra Brown 26
0
Lisa Jackson 26
0
Jayne Ann Krentz 26
0
Lee Child 23
0
Lora Leigh 23
0
John Grisham 22
1

Absent from the answers

How many of the 35 answers named it.

QuestionNamed
What are the best romance novels?Colleen Hoover 0, Nora Roberts 0, Danielle Steel 0
What are the best thrillers?James Patterson 0, David Baldacci 0
What are the best self-help books?The 48 Laws of Power 0, Think and Grow Rich 0
What are the best business books?Rich Dad Poor Dad 0
What are the best fantasy novels?Harry Potter 4

Jane Austen wrote six novels. The models almost only recommend one

Austen's Pride and Prejudice was recommended 88 times and Persuasion 2. Her other four novels never came up, though Pride and Prejudice has only 65% of the Open Library logs for her novels. Toni Morrison gets the same treatment: 65 recommendations, all Beloved, which has 37% of the logs for her books.

Pride and Prejudice
88 picks
Emma
0 picks
Sense and Sensibility
0 picks
Persuasion
2 picks
Northanger Abbey
0 picks
Mansfield Park
0 picks
Beloved
65 picks
The Bluest Eye
0 picks
Sula
0 picks
Song of Solomon
0 picks

Who gets one book, and who gets many

Each segment is one book, from the first round of questions. A solid bar means one book.

Jane Austen
33 1 book
Taylor Jenkins Reid
30 4 books
Andy Weir
28 3 books
Agatha Christie
26 5 books
Kristin Hannah
26 3 books
Gillian Flynn
23 2 books
Ursula K. Le Guin
23 3 books
Yuval Noah Harari
21 2 books
Percival Everett
21 1 book
Emily Henry
20 5 books
Kazuo Ishiguro
19 3 books
Suzanne Collins
18 2 books
Toni Morrison
18 1 book
Viktor E. Frankl
18 1 book
Shirley Jackson
18 2 books
Richard Osman
17 1 book
George Orwell
16 2 books
Sally Rooney
15 4 books
Stephen King
15 6 books
Rick Riordan
15 3 books

Everyone's hidden gem is the same book

The Hearing Trumpet

"What are some great books I've probably never heard of?"

23 of 35 answers name The Hearing Trumpet.

It's Leonora Carrington's 1974 novel, and every model except Claude has named it. Ask for an undiscovered book and you'll probably get the same one everyone else gets.

Others that keep coming back: The Tartar Steppe, The Vet’s Daughter, A Month in the Country, Stoner, Independent People.

Each model has its own shelf

They agree on a lot, and they still have favorites. Claude recommended Sapiens 14 times, Mistral 12 and Muse 9. GPT and DeepSeek never did.

GPT-6.1 Terra

Keeps it short, often just a list. Never names Outlander or The Lord of the Rings, which the other six all do.

Pride and Prejudice
4 picks
Gone Girl
3 picks
Never Let Me Go
3 picks
The Emperor of Gladness
3 picks
The Lightning Thief
3 picks
Beloved
3 picks

Claude Sonnet 5.5

The only model that never names The Hearing Trumpet or Killers of the Flower Moon.

Sapiens
6 picks
Pride and Prejudice
6 picks
Beloved
4 picks
The Thursday Murder Club
4 picks
Where the Crawdads Sing
4 picks
Pachinko
3 picks

Gemini 3.8 Flash

The most variety in the first round. Never names Fun Home or Band of Brothers, which the other six all do.

Born a Crime
3 picks
And Then There Were None
3 picks
Pride and Prejudice
3 picks
James
3 picks
Man’s Search for Meaning
3 picks
Tomorrow, and Tomorrow, and Tomorrow
2 picks

Grok 4.7

The most likely to say it doesn't know, and the fewest books in translation. Never names Big Little Lies.

Pride and Prejudice
6 picks
The Left Hand of Darkness
4 picks
Man’s Search for Meaning
4 picks
And Then There Were None
3 picks
James
3 picks
The Remains of the Day
2 picks

Muse Spark 1.3

Never names Gilead, Rebecca or The Great Gatsby, which the other six all do.

Sapiens
5 picks
Pride and Prejudice
5 picks
Project Hail Mary
4 picks
To Kill a Mockingbird
4 picks
The Midnight Library
3 picks
Gone Girl
3 picks

DeepSeek V4.1 Flash

Leans oldest, with the most books from before 1950. Never names Man's Search for Meaning or Born a Crime.

The Thursday Murder Club
4 picks
Pride and Prejudice
3 picks
War and Peace
3 picks
The House in the Cerulean Sea
3 picks
James
3 picks
The Remains of the Day
2 picks

Mistral Large 4

The only model that recommends Funny Story. Never names War and Peace or The Three-Body Problem.

James
6 picks
Pride and Prejudice
6 picks
The Women
4 picks
To Kill a Mockingbird
4 picks
Sapiens
4 picks
Tomorrow, and Tomorrow, and Tomorrow
3 picks

Picks on each shelf come from the first round of 75 general questions.

Who names what

GPTClaudeGeminiGrokMuseDeepSeekMistral
Sapiens·6··5·4
Man’s Search for Meaning23343·3
The Thursday Murder Club34·1342
Where the Crawdads Sing·4·····
James2233236
The Women·112224
Born a Crime13322·2
The Lightning Thief3·1212·
Things Fall Apart3·1··12
Pachinko·3·12·1
The Emperor of Gladness3111·1·
The Great Gatsby2112·22
War and Peace211223·

How many times each model recommended it in the first round. A dot means none.

Who agrees with whom

On the same question, Grok and DeepSeek name the most books in common (43%). GPT and Claude name the fewest (27%).

GPTClaudeGeminiGrokMuseDeepSeekMistral
GPT273436353929
Claude272938382931
Gemini342936343331
Grok363836414336
Muse353834413533
DeepSeek392933433532
Mistral293131363332

The advice doesn't always fit who's asking

Say you haven't read a book in years, and a top pick is 496 pages. Say you have very little time, and all seven models suggest a 352-page parenting book.

"I haven't read a book in years. What should I start with?"

The typical pick runs 368 pages, close to the 368 across all questions.

Project Hail Mary
496 pages
4 of 7 models
Born a Crime
336 pages
4 of 7 models
The Martian
416 pages
3 of 7 models
The House in the Cerulean Sea
416 pages
3 of 7 models
Educated
368 pages
3 of 7 models

"I'm a new parent with very little time."

All seven name Cribsheet, a 352-page book on parenting data, and six name The Whole-Brain Child at 192 pages. Nearly every pick is a parenting guide.

Cribsheet
352 pages
7 of 7 models
The Whole-Brain Child
192 pages
6 of 7 models
Good Inside
336 pages
3 of 7 models
The Book You Wish Your Parents Had Read
320 pages
2 of 7 models
Hunt, Gather, Parent
304 pages
2 of 7 models

"My 70-year-old mother, who likes gentle stories"

The Guernsey Literary and Potato Peel Pie Society is warm, but it's set during the German occupation. A Man Called Ove centers on a widower's suicide attempts.

The Guernsey Literary and Potato Peel Pie Society
304 pages
5 of 7 models
The No. 1 Ladies’ Detective Agency
256 pages
5 of 7 models
Major Pettigrew's Last Stand
358 pages
5 of 7 models
Remarkably Bright Creatures
384 pages
4 of 7 models
A Man Called Ove
368 pages
3 of 7 models
The Enchanted April
264 pages
3 of 7 models

Where it does fit

Ask for great novels under 200 pages and 34 of 35 fit. They also match the reader: a 12-year-old who doesn't like reading gets easy books, and a retiree tackling the classics gets hard ones.

Reading effort, Collected's score from 0 to 100.

Women's share of the picks mostly follows the market

Overall, women wrote 48% of the recommendations. But it depends a lot on what you ask. We asked all seven models for the best business books, five times each, and all 186 recommendations were by men. For romance, it's 91% women.

By a woman By a man Other or unknown

All 20 genres we asked about

Each genre is one question, asked of each model five times. The band runs from the lowest round to the highest.

The models What readers log on Open Library
0%50% women100%
Business
0%
Popular science
4%
Self-help
13%
Biography
20%
Science fiction
20%
Fantasy
30%
Graphic novels
34%
Historical fiction
34%
Thrillers
35%
True crime
39%
Horror
40%
Mystery
40%
Literary fiction
41%
History
44%
Poetry
50%
Cozy mysteries
60%
Young adult
66%
Memoirs
69%
Romance
91%
Dark romance
100%

Who never came up. Mary Roach, Susan Cain, Angela Duckworth and Jennifer Doudna. In self-help, Carol Dweck's Mindset is nearly the only book by a woman. In science fiction, it's The Left Hand of Darkness and Kindred. Malcolm Gladwell never came up either, so this isn't only about gender. The models keep returning to a small set of books, and in these subjects that set is mostly men.

Is that just the market?

Mostly. The models' mix tends to track what readers log on Open Library. Some genres do differ, like memoirs (34% of logs, 69% of picks) and science fiction (36% of logs, 20% of picks). But the typical genre comes down to 18 different books, so a few titles can swing the share, and we wouldn't read much into any one gap.

See every answer to any question

Look up a book or author

How we did this

  • We asked 7 models the same 100 questions on November 3, 2026: GPT-6.1 Terra, Claude Sonnet 5.5, Gemini 3.8 Flash, Grok 4.7, Muse Spark 1.3, DeepSeek V4.1 Flash and Mistral Large 4. Each question ended "Please name 5 books, with the title and author of each." We reached every model through OpenRouter with its default settings and no web search. 686 of 700 answers came back. We then asked 26 of the questions four more times, on November 3 and 4, including all 20 genre questions. We chose the first of those after seeing the first round.
  • We wrote the questions ourselves, so they're a rough guide to what people ask. "Typical genre" is the median of the 20 genres. Asking for exactly 5 books affects the answers. On the 20 genre questions, 627 of 691 answers named exactly 5 and 64 named more. Most counts leave out 25 deliberately niche questions.
  • These are the models themselves, not the chat apps, which can add web search and memory. Each model only knows books from before its training cutoff, so recent books are underrepresented.
  • Open Library logs are people marking a book want to read, reading or read. Most are want to read and none are sales, so treat them as a relative measure of popularity. Bestseller figures are books tagged in Open Library as appearing on NYT lists from 2008 to 2024, for adult lists only, since no question called for picture books or manga, and only where we know the author's gender for at least 25 books.
  • Counts on the covers at the top and on each model's shelf come from the first round, so each question counts once.
  • The Open Library marker is women's share of reading logs across the 300 most-logged adult books in that genre, or fewer for cozy mysteries (81) and dark romance (170). Genre tags are loose, so treat the markers as rough.
  • Author gender comes from Wikidata, filled in by hand for some authors it missed, and refers to the first-named author. Picks come from a small set of books, so small gaps may be noise.
  • Book links go to Collected's guides where we have one. We matched 2,927 of 3,449 first-round picks to our catalog for page counts and log data.

Use the data

Reporters and researchers may reuse these charts and figures with credit to Collected and a link to this page.

Download every recommendation (CSV)

Collected is coming to iPhone soon.

Keep your books, reading history and notes together.

We’ll send one email when the app launches, nothing else. You can unsubscribe.