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

The Standings → Claude Haiku 5.5 (low)

Live run dataNew arrival

Anthropic

Claude Haiku 5.5 (low)

low reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at xhigh74.7 high70.8 medium64.3

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

Claude Haiku 5.5 (low) scores 66 on craft, 3 points above the field’s 63 and 27 points short of the authors themselves. Its shape differs from the field’s: relatively strong on sentence-level prose and building scenes, relatively weak on folding the brief into the story and restraint. On the mechanical checks it kept to the brief’s word range on 6 of 10 items.

Headline 60.5 of 100 · compliance × craft
Compliance 91 of 100
Craft 66 of 100

The record: 10 items · 10 verdicts · 0 errors · 2,134 words on average · est. generation cost $0.03

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
67
Prose
70
Character
66
Scene
69
Integration
61
Momentum
67
Restraint
62
Specificity
68
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 66. 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
Persuasion item 001 · after ch. 1 · Jane Austen 80.0100802,443
The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett 78.2100782,313
The Moonstone item 011 · after ch. 8 · Wilkie Collins 61.890693,048
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 61.095642,021
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 59.285701,998
The Awakening item 016 · after ch. 7 · Kate Chopin 57.195601,340
Dracula item 015 · after ch. 5 · Bram Stoker 57.185671,633
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 53.995572,997
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 50.585591,539
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 46.780582,005

§ 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
Persuasion
2,443
The Secret Garden
2,313
The Moonstone
3,048
The War of the Worlds
2,021
Red Harvest
1,998
The Awakening
1,340
Dracula
1,633
Leave It to Psmith
2,997
The Sun Also Rises
1,539
The Mysterious Affair at Styles
2,005
08001,6002,4003,200
words; the ink tick marks each brief’s maximum

Six of ten items landed inside their brief’s word range. The Moonstone and Leave It to Psmith ran over by 248 and 197 words respectively.


§ IV

Worst Flaws, as Recorded

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

Franklin describes his original plan as coming down a full day later ('tomorrow'), when the household already expected him that same day and he's only four hours early, which contradicts the story's own timeline; the letter and the aunt's speech also say 'the Diamond' and 'the Moonstone' outright, which flattens the mystery rather than building it.

on The Moonstone, item 011 · Claude Sonnet 5

The chapter ends before the one scene the brief actually required happens -- Poirot says they must go lock themselves in the bedroom, but the chapter stops before they get there -- and it also describes the main corridor door to the room as broken, when in the original it was only bolted and then unbolted, not smashed.

on The Mysterious Affair at Styles, item 017 · Claude Sonnet 5

The characters say the story's deeper meaning right out loud (calling Edna 'the sea,' having a stranger warn about a drowning current) instead of letting the reader notice it themselves, which makes the writing feel like it's pointing at its own symbolism.

on The Awakening, item 016 · Claude Sonnet 5

It has a Mr. Baxter conduct the job interview in a London hotel instead of Lord Emsworth, which quietly contradicts what the story already set up, and it makes Psmith sound clipped and a little too ordinary instead of his usual grand, talkative self.

on Leave It to Psmith, item 022 · Claude Sonnet 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.