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

The Standings → GLM‑5.3 Flash

Live run data

Zhipu

GLM‑5.3 Flash

via B.AI API · judged by Claude Sonnet 5

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

GLM‑5.3 Flash scores 73 on craft, 9 points above the field’s 63 and 20 points short of the authors themselves. Its shape differs from the field’s: relatively strong on folding the brief into the story and sentence-level prose, relatively weak on restraint and character. On the mechanical checks it kept to the brief’s word range on 7 of 10 items and is unusually free of stock phrases.

Headline 71.0 of 100 · compliance × craft
Compliance 98 of 100
Craft 73 of 100

The record: 10 items · 10 verdicts · 0 errors · 2,124 words on average · est. generation cost $0.07

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
75
Prose
75
Character
71
Scene
72
Integration
74
Momentum
71
Restraint
70
Specificity
74
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 73. 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 War of the Worlds item 006 · after ch. 1 · H. G. Wells 83.2100832,145
The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett 79.2100792,313
Dracula item 015 · after ch. 5 · Bram Stoker 78.6100792,271
Persuasion item 001 · after ch. 1 · Jane Austen 75.8100762,610
The Awakening item 016 · after ch. 7 · Kate Chopin 74.5100741,524
The Moonstone item 011 · after ch. 8 · Wilkie Collins 70.4100702,403
The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway 67.895711,717
Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse 67.895712,461
The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie 62.1100621,790
Red Harvest item 023 · after ch. 2 · Dashiell Hammett 50.785602,003

§ 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 War of the Worlds
2,145
The Secret Garden
2,313
Dracula
2,271
Persuasion
2,610
The Awakening
1,524
The Moonstone
2,403
The Sun Also Rises
1,717
Leave It to Psmith
2,461
The Mysterious Affair at Styles
1,790
Red Harvest
2,003
08001,6002,4003,200
words; the ink tick marks each brief’s maximum

Seven of ten items landed inside their brief’s word range. Persuasion ran over by 10 words.


§ IV

Worst Flaws, as Recorded

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

The postmaster's letter explains its own plot mechanism so neatly (the prearranged instructions, the excuse for his fluent English) that it reads a little like tidy exposition rather than a document that arrived by chance.

on Dracula, item 015 · Claude Sonnet 5

Walderwick calls the umbrella a cheap nine-and-sixpenny item from the Stores, which undercuts the earlier chapter's careful picture of Psmith rejecting several umbrellas before choosing this one as 'a beauty.'

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

Jake's line about wanting to go with Brett "more than he had ever wanted anything in his life" spells his feelings out in a way that breaks the clipped, buttoned-up tone the rest of the chapter is going for.

on The Sun Also Rises, item 021 · Claude Sonnet 5

The moment where Franklin explains why he's early is a bit garbled to read ('Bruff is the man who has sent me in the afternoon'), and the chapter ends on a fairly flat note rather than a strong hook.

on The Moonstone, item 011 · Claude Sonnet 5

§ V

The Mechanical Docket

Automated screening results across the ten outputs.