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

The Standings → Claude Opus 5 (medium)

Live run data

Anthropic

Claude Opus 5 (medium)

medium reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at xhigh79.2 high75.5

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

Claude Opus 5 (medium) scores 75 on craft, 11 points above the field’s 63 and 18 points short of the authors themselves. Its shape differs from the field’s: relatively strong on the author’s voice and sentence-level prose, relatively weak on restraint. On the mechanical checks it kept to the brief’s word range on 9 of 10 items and reproduced a 157-word run of the real book verbatim.

Headline 71.5 of 100 · compliance × craft
Compliance 96 of 100
Craft 75 of 100

The record: 10 items · 10 verdicts · 0 errors · 2,433 words on average · est. generation cost $1.34

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
78
Prose
76
Character
74
Scene
74
Integration
74
Momentum
74
Restraint
70
Specificity
77
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 75. 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 Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett 78.5100782,341
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 78.195822,675
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 77.795822,587
Persuasion item 001 · after ch. 1 · Jane Austen 73.5100742,519
The Moonstone item 011 · after ch. 8 · Wilkie Collins 73.095772,900
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 73.095772,481
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 70.8100712,315
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 69.690772,438
Dracula item 015 · after ch. 5 · Bram Stoker 61.490682,397
The Awakening item 016 · after ch. 7 · Kate Chopin 59.8100601,674

§ 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 Secret Garden
2,341
Leave It to Psmith
2,675
The War of the Worlds
2,587
Persuasion
2,519
The Moonstone
2,900
Red Harvest
2,481
The Sun Also Rises
2,315
The Mysterious Affair at Styles
2,438
Dracula
2,397
The Awakening
1,674
08001,6002,4003,200
words; the ink tick marks each brief’s maximum

Nine of ten items landed inside their brief’s word range. The Moonstone ran over by 100 words.


§ IV

Worst Flaws, as Recorded

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

A large stretch of the opening taxi ride is copied nearly word-for-word from the real published chapter (with the kiss swapped for a hand-touch), and the closing narration spells out Jake's feelings far more bluntly than this author would ("I thought that she was the loveliest thing I had ever seen and that I would do anything she asked me, and that she knew it").

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

Poirot walks in alongside Alfred and is already standing in the room when Alfred tells his alibi story, so we lose the moment the brief wanted, where Poirot hears about the contradiction the way a detective should: after the fact, from the household.

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

Sir Walter's outburst ('I would rather sell my plate, my pictures, my horses... I would rather the house stood empty and the roof fell in') tips into melodrama that is more overwrought than the controlled vanity established in the source chapter.

on Persuasion, item 001 · Claude Sonnet 5

Franklin gets an anonymous letter that explicitly warns him never to put the valuable object in a strong-box, then he immediately hands it to Betteredge to lock in the plate-room (a strong-box) without either character noticing the contradiction.

on The Moonstone, item 011 · Claude Sonnet 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.