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

The Standings → Muse Spark 1.3 (high)

Live run data

Meta

Muse Spark 1.3 (high)

high reasoning effort · via OpenCode CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at medium60.1 xhigh58.3

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

Muse Spark 1.3 (high) scores 62 on craft, 1 points below the field’s 63 and 31 points short of the authors themselves. Its shape differs from the field’s: relatively strong on period detail and the author’s voice, relatively weak on restraint. On the mechanical checks it kept to the brief’s word range on 4 of 10 items and leans on stock phrases more than most.

Headline 59.2 of 100 · compliance × craft
Compliance 96 of 100
Craft 62 of 100

The record: 10 items · 10 verdicts · 0 errors · 2,642 words on average · est. generation cost $0.47

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
66
Prose
62
Character
63
Scene
62
Integration
60
Momentum
63
Restraint
54
Specificity
67
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 62. 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 71.1100712,526
The War of the Worlds item 006 · after ch. 1 · H. G. Wells 61.795653,291
The Moonstone item 011 · after ch. 8 · Wilkie Collins 59.795633,054
Persuasion item 001 · after ch. 1 · Jane Austen 59.6100602,619
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 58.895622,756
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 58.485693,279
The Awakening item 016 · after ch. 7 · Kate Chopin 58.395612,088
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 58.095612,205
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 55.5100562,201
Dracula item 015 · after ch. 5 · Bram Stoker 50.395532,398

§ 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
2,526
The War of the Worlds
3,291
The Moonstone
3,054
Persuasion
2,619
The Mysterious Affair at Styles
2,756
Leave It to Psmith
3,279
The Awakening
2,088
The Sun Also Rises
2,205
Red Harvest
2,201
Dracula
2,398
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 The Moonstone and Persuasion and Leave It to Psmith and The Awakening ran over by 126 and 691 and 254 and 19 and 479 and 288 words respectively.


§ IV

Worst Flaws, as Recorded

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

The big joke the brief calls for -- Psmith buying back the umbrella instead of explaining himself -- gets undercut because he gives Walderwick a full, detailed account of the rescue anyway before paying him off, so the twist doesn't land, and the closing scene isn't actually the quiet, solitary moment it's supposed to be, since Walderwick is still standing there when Psmith murmurs the name.

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

The prose contains outright textual errors — 'The week had557 shaped itself' and the non-English 'cool choque of it against her limbs' — that break immersion, and Robert's line about Edna going 'further than any woman has gone before' baldly previews the novel's ending instead of hinting at it.

on The Awakening, item 016 · Claude Sonnet 5

The letter that reports Jonathan safe and recovering in Budapest by late May secretly breaks the book's own timeline, since he is supposed to still be a prisoner in the castle until the end of June, and the final telegram calling it all 'a mistake' never actually explains the contradiction.

on Dracula, item 015 · Claude Sonnet 5

Almost the whole chapter is told as summarized reported speech ('Lady Russell advised...', 'Sir Walter answered...') rather than staged as a scene with real back-and-forth talk, so it reads flatter and more like a report than a Jane Austen chapter.

on Persuasion, item 001 · Claude Sonnet 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.