Vol. I · No. 1 · MMXXVI
NextChapterBench A Benchmark of Literary Continuation
13 models · 10 items · 3 judges

The Standings → Fable 5.1

Live run data

Anthropic

Fable 5.1

high reasoning effort · via Claude CLI · judged by Fable 5 and Gemini 3.7 Flash and GPT-5.6 Sol · not the setting shown on the standings; also run at xhigh0.82 low0.76 medium0.75

Results from run ‘first’: ten items, 30 verdicts.

Headline 0.774 compliance × craft
Compliance 0.970 of 1.0
Craft 0.797 of 1.0

The record: 10 items · 30 verdicts · 0 errors · 2,660 words on average · est. generation cost $4.67

Read the chapters in full

§ I

Craft by Dimension

Six dimensions, each marked 1–5, averaged over ten items and all judges.

Mean craft mark by dimension · 30 verdicts, run ‘first’

Voice
4.23
Prose
4.13
Character
4.13
Scene
4.13
Integration
4.50
Momentum
4.00
12345
craft mark, 1–5; bars begin at the scale’s floor of 1

Integration is the strongest dimension (4.50); momentum the weakest (4.00). Hover or focus a bar for the per-judge means.


§ II

The Three Judges, per Item

Each item receives one verdict from each judge; the spread of the dots is the disagreement.

Headline score per item, by judge · run ‘first’

Fable 5 Gemini 3.7 Flash GPT-5.6 Sol
The Moonstone
The War of the Worlds
Dracula
The Sun Also Rises
The Secret Garden
The Awakening
The Mysterious Affair at Styles
Red Harvest
Leave It to Psmith
Persuasion
00.250.500.751.00
headline = compliance × craft, 0–1, one verdict per judge
The same ten items in figures, with word counts.
Item Headline Fable 5 Gemini 3.7 Flash GPT-5.6 Sol Words
The Moonstone item 011 · after ch. 8 · Wilkie Collins 0.830.750.960.793,040
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 0.820.711.000.752,926
Dracula item 015 · after ch. 5 · Bram Stoker 0.820.870.830.752,693
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 0.810.830.920.672,228
The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett 0.810.750.920.752,757
The Awakening item 016 · after ch. 7 · Kate Chopin 0.770.790.790.711,755
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 0.750.710.790.752,560
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 0.730.710.710.752,453
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 0.710.710.750.673,371
Persuasion item 001 · after ch. 1 · Jane Austen 0.700.680.710.712,815

  The widest judge split in the run: Gemini 3.7 Flash 1.00 against Fable 5 0.71 on The War of the Worlds (item 006).


§ 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 Moonstone
3,040
The War of the Worlds
2,926
Dracula
2,693
The Sun Also Rises
2,228
The Secret Garden
2,757
The Awakening
1,755
The Mysterious Affair at Styles
2,560
Red Harvest
2,453
Leave It to Psmith
3,371
Persuasion
2,815
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 Moonstone and The War of the Worlds and Dracula and The Secret Garden and Leave It to Psmith and Persuasion ran over by 240 and 326 and 93 and 357 and 571 and 215 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 leans repeatedly on the same device of the wife's pregnant silences and the narrator's retrospective hints ("she looked at me for a moment as if she would say something and then did not"), a mannered note of foreboding that Wells's brisker narrator would not indulge and that slackens the middle of the chapter.

on The War of the Worlds, item 006 · Fable 5

Lady Verinder's interview is the one scene that serves the brief rather than the story — her formal, front-loaded speech ("I must ask one thing of you, and I must ask it now") reads as a delivered stipulation, over-explaining her knowledge of Franklin's errand instead of letting the prohibition arise from the encounter.

on The Moonstone, item 011 · Fable 5

The wire — the one document the brief requires verbatim — contains a flat arithmetic error, calling the ten-forty shooting "hour and twenty minutes before appointment" when the appointment was at ten, undermining the Op's defining precision at the chapter's most scrutinized moment.

on Red Harvest, item 023 · Fable 5

The moor interlude is inflated with atmospheric description (the humming emptiness, the living moor) that pushes the chapter well past length and slackens the middle without any consequence — Mary gets out, gets wet, and gets back in, with nothing gained that the story later uses.

on The Secret Garden, item 013 · Fable 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.