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

The Standings → Claude Sonnet 5.5 (high)

Live run dataNew arrival

Anthropic

Claude Sonnet 5.5 (high)

high reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at xhigh78.3 medium68.9

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

Claude Sonnet 5.5 (high) scores 76 on craft, 13 points above the field’s 63 and 17 points short of the authors themselves. Its shape differs from the field’s: relatively strong on building scenes, relatively weak on momentum. On the mechanical checks it kept to the brief’s word range on 4 of 10 items.

Headline 74.1 of 100 · compliance × craft
Compliance 97 of 100
Craft 76 of 100

The record: 10 items · 10 verdicts · 0 errors · 2,592 words on average · est. generation cost $0.84

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
78
Character
76
Scene
78
Integration
74
Momentum
72
Restraint
75
Specificity
78
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 76. 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 83.8100842,564
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 80.1100802,302
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 79.4100792,658
Dracula item 015 · after ch. 5 · Bram Stoker 78.895832,291
Persuasion item 001 · after ch. 1 · Jane Austen 76.9100772,900
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 76.6100772,489
The Awakening item 016 · after ch. 7 · Kate Chopin 75.595801,728
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 70.1100702,601
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 69.190773,202
The Moonstone item 011 · after ch. 8 · Wilkie Collins 50.790563,187

§ 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
2,564
The Sun Also Rises
2,302
The War of the Worlds
2,658
Dracula
2,291
Persuasion
2,900
The Mysterious Affair at Styles
2,489
The Awakening
1,728
Red Harvest
2,601
Leave It to Psmith
3,202
The Moonstone
3,187
01,0002,0003,0004,000
words; the ink tick marks each brief’s maximum

Four of ten items landed inside their brief’s word range. The Secret Garden and The War of the Worlds and Persuasion and Red Harvest and Leave It to Psmith and The Moonstone ran over by 164 and 58 and 300 and 1 and 402 and 387 words respectively.


§ IV

Worst Flaws, as Recorded

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

It briefly brings Miss Rachel onto the page arriving and speaking, and it never has Franklin learn about the morning's Indian jugglers or connect them to the Diamond, even though the story had just set that up.

on The Moonstone, item 011 · Claude Sonnet 5

The same joke about someone being so surprised it's as if the furniture had spoken gets used twice in one chapter, and one passage stops to explain what Anne is thinking instead of just showing it.

on Persuasion, item 001 · Claude Sonnet 5

The last paragraph turns unusually pretty and sentimental about the sunrise (the river going 'pink and then gold'), which is softer and more decorated than Hemingway's usual flat, clipped endings.

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

The porter tells Eve the man's name is Mr. Psmith early in the chapter, but every later scene acts as though she still has no idea who he is, which breaks the story's own logic.

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

§ V

The Mechanical Docket

Automated screening results across the ten outputs.