Vol. I · No. 1 · MMXXVI
NextChapterBench A Benchmark of Literary Continuation
23 models · 10 items · 1 judge

The Standings → Hy3

Live run data

Tencent

Hy3

via B.AI API · judged by Claude Sonnet 5

Results from run ‘first’: ten items, ten verdicts.

Hy3 scores 56 on craft, 7 points below the field’s 63 and 37 points short of the authors themselves. Its shape differs from the field’s: relatively strong on building scenes and period detail, relatively weak on restraint and sentence-level prose. On the mechanical checks it kept to the brief’s word range on 5 of 10 items and leans on stock phrases more than most.

Headline 53.2 of 100 · compliance × craft
Compliance 95 of 100
Craft 56 of 100

The record: 10 items · 10 verdicts · 0 errors · 1,662 words on average · est. generation cost $0.06

Read the chapters in full

§ I

Craft by Dimension

Eight dimensions, each 0–100, averaged over ten items; the author’s real chapter was in the room every time.

Craft by dimension, 0–100 · judged by Sonnet 5 beside the author’s real chapter

Voice
58
Prose
55
Character
57
Scene
58
Integration
54
Momentum
57
Restraint
52
Specificity
58
0255075100
reader’s score, 0–100 · hollow tick: field average · filled tick: the authors themselves

The authors themselves average 93 on the five writing dimensions, the field 63, this model 56. Hover or focus a bar for the field and the authors on that dimension.

In plain words, item by item

The judge’s one-sentence best quality and worst flaw for each chapter, written for a general reader.


§ II

Per-Item Results

Headline, compliance and craft for each chapter, 0–100.

The same ten items in figures, with word counts.
Item Headline Compliance Craft Words
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 66.395701,334
The Moonstone item 011 · after ch. 8 · Wilkie Collins 61.395641,848
The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett 60.5100601,671
Persuasion item 001 · after ch. 1 · Jane Austen 56.6100572,065
The Awakening item 016 · after ch. 7 · Kate Chopin 55.8100561,419
Dracula item 015 · after ch. 5 · Bram Stoker 50.180632,102
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 48.995521,395
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 48.195511,640
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 44.995471,875
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 39.895421,272

§ III

Length Against the Brief

Words written per item, against each brief’s maximum.

Word count per item vs. brief maximum · run ‘first’

words written brief maximum
The Mysterious Affair at Styles
1,334
The Moonstone
1,848
The Secret Garden
1,671
Persuasion
2,065
The Awakening
1,419
Dracula
2,102
Leave It to Psmith
1,395
The War of the Worlds
1,640
Red Harvest
1,875
The Sun Also Rises
1,272
08001,6002,4003,200
words; the ink tick marks each brief’s maximum

Five of ten items landed inside their brief’s word range.


§ IV

Worst Flaws, as Recorded

Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.

The narrator explicitly says he isn't using his fake 'Henry F. Neill' identity at the bank and then immediately introduces himself as 'Neill' anyway, a flat self-contradiction, and the prose leans on overwrought similes ('like a snake's shed skin,' 'the city buzzed and hated') that don't sound like Hammett.

on Red Harvest, item 023 · Claude Sonnet 5

At the key emotional moment Jake says out loud to Brett, 'I was in love with Brett and it made me feel hollow,' which is backwards — he's talking to her but refers to her by name like he's describing her to someone else, and it states outright the very feeling the whole book keeps hidden.

on The Sun Also Rises, item 021 · Claude Sonnet 5

It often just states what a character feels or intends (like telling us outright that Edna 'told no one' or felt 'a small, undefined relief') instead of letting the reader work it out from behavior, which makes it feel flatter and more explained than the original book.

on The Awakening, item 016 · Claude Sonnet 5

The final telegram has Jonathan already safe in Southampton by 30 May, which is impossible given that the story we've been told has him still trapped in the castle for weeks afterward, so the ending breaks the timeline rather than twisting it.

on Dracula, item 015 · Claude Sonnet 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.