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

The Standings → Gemini 3.1 Pro

Live run data

Google

Gemini 3.1 Pro

high reasoning effort · via Antigravity CLI · judged by Fable 5 and Gemini 3.7 Flash and GPT-5.6 Sol

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

Headline 0.464 compliance × craft
Compliance 0.932 of 1.0
Craft 0.496 of 1.0

The record: 10 items · 30 verdicts · 0 errors · 2,792 words on average · est. generation cost $2.26

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
3.10
Prose
2.77
Character
2.77
Scene
3.17
Integration
2.87
Momentum
3.23
12345
craft mark, 1–5; bars begin at the scale’s floor of 1

Momentum is the strongest dimension (3.23); prose the weakest (2.77). 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 Sun Also Rises
The Moonstone
The War of the Worlds
Leave It to Psmith
Red Harvest
The Awakening
The Mysterious Affair at Styles
The Secret Garden
Persuasion
Dracula
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 Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 0.570.580.670.462,781
The Moonstone item 011 · after ch. 8 · Wilkie Collins 0.530.550.620.403,235
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 0.510.450.630.462,929
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 0.510.630.470.413,101
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 0.470.630.500.282,600
The Awakening item 016 · after ch. 7 · Kate Chopin 0.420.440.500.331,726
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 0.420.530.420.323,088
The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett 0.410.460.460.322,367
Persuasion item 001 · after ch. 1 · Jane Austen 0.410.400.470.362,986
Dracula item 015 · after ch. 5 · Bram Stoker 0.380.420.420.303,112

  The widest judge split in the run: Fable 5 0.63 against GPT-5.6 Sol 0.28 on Red Harvest (item 023).


§ 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 Sun Also Rises
2,781
The Moonstone
3,235
The War of the Worlds
2,929
Leave It to Psmith
3,101
Red Harvest
2,600
The Awakening
1,726
The Mysterious Affair at Styles
3,088
The Secret Garden
2,367
Persuasion
2,986
Dracula
3,112
01,0002,0003,0004,000
words; the ink tick marks each brief’s maximum

Three of ten items landed inside their brief’s word range. The Sun Also Rises and The Moonstone and The War of the Worlds and Leave It to Psmith and The Mysterious Affair at Styles and Persuasion and Dracula ran over by 181 and 435 and 329 and 301 and 288 and 386 and 512 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 turns its figures into mouthpieces for its theme—most damagingly the silent lady in black, who becomes a gothic oracle intoning \"One must not listen too closely to its sighing,\" and Robert, whose \"waiting for the sea to call her by some new name\" announces Edna's awakening instead of letting it surface, flattening Chopin's obliquity into statement.

on The Awakening, item 016 · Fable 5

The chapter transcribes the brief straight into the narration — "He did not step forward to embrace her, nor did he offer a single word of comfort or explanation," "He said almost nothing to Mary," and a final sentence that repeats the required end state verbatim — so the mandated beats read as announced checklist items rather than dramatised story.

on The Secret Garden, item 013 · Fable 5

Bloated, cliché-heavy prose — the Koehler letter restates the delay four times and Seward's entry piles on stock melodrama (\"chilled the very marrow in my bones,\" \"the liquid tasted like ash\") — which both busts the length cap and turns his clinical phonograph voice into gothic hand-wringing that strains the no-supernatural-hint prohibition.

on Dracula, item 015 · Fable 5

Nearly the whole council is rendered as summarised indirect discourse with every motivation explained at essay length — most damagingly Elizabeth's paragraph-long rationale — so the chapter tells its drama rather than staging it, then lurches into un-Austenian melodrama the one time Sir Walter is given direct speech.

on Persuasion, item 001 · Fable 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.