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

The Standings → Claude Haiku 5.5 (medium)

Live run dataNew arrival

Anthropic

Claude Haiku 5.5 (medium)

medium reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at xhigh74.7 high70.8 low60.5

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

Claude Haiku 5.5 (medium) scores 68 on craft, 5 points above the field’s 63 and 25 points short of the authors themselves. Its shape differs from the field’s: relatively strong on restraint and period detail, relatively weak on folding the brief into the story and building scenes. On the mechanical checks it kept to the brief’s word range on 6 of 10 items and is unusually free of stock phrases.

Headline 64.3 of 100 · compliance × craft
Compliance 94 of 100
Craft 68 of 100

The record: 10 items · 10 verdicts · 0 errors · 2,143 words on average · est. generation cost $0.05

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
69
Prose
70
Character
67
Scene
67
Integration
63
Momentum
70
Restraint
69
Specificity
72
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 68. 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 82.4100822,170
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 77.1100771,858
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 71.390792,519
Persuasion item 001 · after ch. 1 · Jane Austen 66.395702,845
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 64.095672,229
The Awakening item 016 · after ch. 7 · Kate Chopin 62.195651,411
The Moonstone item 011 · after ch. 8 · Wilkie Collins 57.790642,883
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 56.395591,768
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 53.995572,125
Dracula item 015 · after ch. 5 · Bram Stoker 51.885611,621

§ 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
2,170
The Sun Also Rises
1,858
Leave It to Psmith
2,519
Persuasion
2,845
The War of the Worlds
2,229
The Awakening
1,411
The Moonstone
2,883
Red Harvest
1,768
The Mysterious Affair at Styles
2,125
Dracula
1,621
08001,6002,4003,200
words; the ink tick marks each brief’s maximum

Six of ten items landed inside their brief’s word range. Persuasion and The Moonstone ran over by 245 and 83 words respectively.


§ IV

Worst Flaws, as Recorded

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

The chapter ends with Psmith's friend Mike still sitting right there in the room, so the quiet, private moment the story needed doesn't quite happen, and Psmith barely uses his trademark habit of calling people 'Comrade,' so he sounds a little less like himself.

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

At one point it's unclear whether Anne is actually in the room during the big scene with Mr Shepherd, since the text first has her walking away up to her room and then has her watching her father's face as if she'd been there the whole time, which is confusing.

on Persuasion, item 001 · Claude Sonnet 5

It accidentally breaks the story's own logic by having Betteredge say the trance-boy actually spoke the word 'Moonstone,' when in the source material the boy only ever says 'It' and nobody has named the diamond yet.

on The Moonstone, item 011 · Claude Sonnet 5

The chapter skips the actual moment Robert says something to Adèle during the walk — it tells us Edna couldn't hear it and only reports it secondhand later, so the required scene is talked about rather than shown.

on The Awakening, item 016 · Claude Sonnet 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.