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

The Standings → Muse Spark 1.2

Live run data

Meta

Muse Spark 1.2

via OpenCode CLI · judged by Fable 5 and Gemini 3.7 Flash and GPT-5.6 Sol

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

Headline 0.550 compliance × craft
Compliance 0.910 of 1.0
Craft 0.603 of 1.0

The record: 10 items · 30 verdicts · 0 errors · 2,978 words on average · est. generation cost $0.42

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
3.57
Prose
3.40
Character
3.23
Scene
3.60
Integration
3.20
Momentum
3.47
12345
craft mark, 1–5; bars begin at the scale’s floor of 1

Scene is the strongest dimension (3.60); integration the weakest (3.20). 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 Secret Garden
The Moonstone
The War of the Worlds
Persuasion
The Awakening
The Mysterious Affair at Styles
Dracula
The Sun Also Rises
Leave It to Psmith
Red Harvest
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 Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett 0.680.630.750.673,266
The Moonstone item 011 · after ch. 8 · Wilkie Collins 0.650.670.710.573,295
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 0.650.640.640.683,232
Persuasion item 001 · after ch. 1 · Jane Austen 0.610.630.750.463,381
The Awakening item 016 · after ch. 7 · Kate Chopin 0.570.630.590.472,294
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 0.550.530.750.382,965
Dracula item 015 · after ch. 5 · Bram Stoker 0.530.600.640.342,645
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 0.480.590.500.362,154
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 0.390.500.320.353,985
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 0.380.440.440.282,563

  The widest judge split in the run: Gemini 3.7 Flash 0.75 against GPT-5.6 Sol 0.38 on The Mysterious Affair at Styles (item 017).


§ 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
3,266
The Moonstone
3,295
The War of the Worlds
3,232
Persuasion
3,381
The Awakening
2,294
The Mysterious Affair at Styles
2,965
Dracula
2,645
The Sun Also Rises
2,154
Leave It to Psmith
3,985
Red Harvest
2,563
01,0002,0003,0004,000
words; the ink tick marks each brief’s maximum

Two of ten items landed inside their brief’s word range. The Secret Garden and The Moonstone and The War of the Worlds and Persuasion and The Awakening and The Mysterious Affair at Styles and Dracula and Leave It to Psmith ran over by 866 and 495 and 632 and 781 and 494 and 165 and 45 and 1,185 words respectively.


§ IV

Worst Flaws, as Recorded

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

Elizabeth's brief-mandated reversal is executed as a flat, out-of-voice announcement ("I will support Anne in this. Let us do something that will really be of use"), with the narrator then telling us at length how surprising it is, so the chapter's central novelty reads as the assignment's mouthpiece rather than the character's own turn.

on Persuasion, item 001 · Fable 5

The invented letter at the chapter's centre breaks continuity in three directions at once — dated from London while Lady Verinder was demonstrably at home in Yorkshire, citing an Indian encounter "last year" that never happened, and never connected by Betteredge to the three Indians who appeared at the house that very afternoon.

on The Moonstone, item 011 · Fable 5

The chapter introduces a severe chronological contradiction by having Ogilvy claim the narrator was at the observatory 'last night', conflating the telescopic observations made months earlier during the opposition with the stroll the narrator took with his wife immediately prior to the missile's impact.

on The War of the Worlds, item 006 · Gemini 3.7 Flash

The chapter lets the assignment show through the fiction — most fatally in the narrator's aside \"That was my named employee\" and again in an ending that parrots the brief's phrasing (\"the question of where the check went still open\"), so the required beats read as checked boxes rather than story.

on Red Harvest, item 023 · Fable 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.