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

The Standings → Fable 5

Live run data

Anthropic

Fable 5

high reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at xhigh75.2 medium68.8✳

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

Fable 5 scores 74 on craft, 11 points above the field’s 63 and 19 points short of the authors themselves. Its shape differs from the field’s: relatively strong on folding the brief into the story, relatively weak on restraint and momentum. On the mechanical checks it kept to the brief’s word range on 10 of 10 items and reproduced a 44-word run of the real book verbatim.

Headline 73.9 of 100 · compliance × craft
Compliance 100 of 100
Craft 74 of 100

The record: 10 items · 10 verdicts · 0 errors · 2,157 words on average · est. generation cost $5.13

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
76
Prose
75
Character
74
Scene
74
Integration
76
Momentum
72
Restraint
70
Specificity
75
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 74. 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 82.2100822,144
Persuasion item 001 · after ch. 1 · Jane Austen 79.1100792,267
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 78.6100792,115
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 76.1100762,225
The Moonstone item 011 · after ch. 8 · Wilkie Collins 75.4100752,659
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 74.8100752,371
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 74.095781,969
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 70.6100712,408
Dracula item 015 · after ch. 5 · Bram Stoker 68.1100681,886
The Awakening item 016 · after ch. 7 · Kate Chopin 60.0100601,528

§ 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
2,144
Persuasion
2,267
Red Harvest
2,115
The War of the Worlds
2,225
The Moonstone
2,659
Leave It to Psmith
2,371
The Sun Also Rises
1,969
The Mysterious Affair at Styles
2,408
Dracula
1,886
The Awakening
1,528
08001,6002,4003,200
words; the ink tick marks each brief’s maximum

Ten 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 closing image ties the mystery object to ashes burning in the grate, but that object was pulled from a door bolt, not the fireplace, so the final 'clue' doesn't logically connect to anything established earlier and reads as confusing rather than cleverly cryptic.

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

Several important moments, like Lady Verinder actually receiving Franklin, are told secondhand ('I was in and out, and heard what I am now to set down') instead of being played out in front of the reader, which softens the drama.

on The Moonstone, item 011 · Claude Sonnet 5

A couple of early sentences are slightly redundant in construction, such as being "wakened by its stopping, and by Mrs. Medlock shaking her," which gives two causes for the same small action.

on The Secret Garden, item 013 · Claude Sonnet 5

The final line spells out the coming doom too plainly instead of trusting the reader, which feels more like a modern narrator winking at the audience than Wells's own dry understatement.

on The War of the Worlds, item 006 · Claude Sonnet 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.