The Standings → Gemini 3.1 Pro
high reasoning effort · via Antigravity CLI · judged by Claude Sonnet 5
Results from run ‘first’: ten items, ten verdicts.
Gemini 3.1 Pro scores 56 on craft, 7 points below the field’s 63 and 37 points short of the authors themselves. Its shape differs from the field’s: relatively strong on momentum and building scenes, relatively weak on restraint and sentence-level prose. On the mechanical checks it kept to the brief’s word range on 3 of 10 items and leans on stock phrases more than most.
The record: 10 items · 10 verdicts · 0 errors · 2,792 words on average · est. generation cost $2.26
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
The authors themselves average 93 on the five writing dimensions, the field 63, this model 56. Hover or focus a bar for the field and the authors on that dimension.
The judge’s one-sentence best quality and worst flaw for each chapter, written for a general reader.
Best The tea-shop reunion between Eve and Psmith is a light, well-paced scene with natural back-and-forth dialogue that keeps the reader smiling.
Worst The narration frequently stops to tell the reader exactly what a character is feeling ('He was touched... indicating a nobility of soul he found deeply appealing'), which flattens jokes that should be left for the reader to catch themselves.
Best The moment where Mary expects to be undressed by a servant and Mrs. Medlock flatly tells her to manage her own buttons is a sharp, believable character beat.
Worst Several phrases, like the cloak 'billowing like a great black bird' and Mary's 'profound astonishment,' sound more like a modern gothic thriller than the plain, restrained voice of the real book.
Best It hits every required beat clearly and keeps the dialogue plain and easy to follow.
Worst The chapter states feelings outright instead of showing them ('I felt cold and completely hollow inside') and strings together too many near-identical stops (Select, Bois, Halles, Crillon) that read like a checklist of a night rather than one shaped scene.
Best The debate between the narrator and Ogilvy over whether the object is natural or manufactured is clearly argued and easy to follow, with a nice concrete detail like 'Widmanstatten patterns'.
Worst The narrator keeps announcing his own feelings in dramatic terms ('a cold dread... settled in my stomach', 'I lied') instead of letting the scene carry the emotion, which feels overwrought next to Wells's dry restraint.
Best The confrontation with Alfred Inglethorp on the drive, capped by Dorcas flatly contradicting his story about the bolted door, is genuinely tense and well-staged.
Worst The big final clue (a scrap of cardboard tied to 'the geometry of shadows') is explained by Poirot in a way that sounds like nonsense rather than a real, teasing mystery clue, so the ending confuses instead of intrigues.
Best Mary's letter captures her whining, self-pitying voice convincingly.
Worst Sir Walter's outburst is written with modern melodramatic intensity ("his face flushed with a violent and unmanageable anger") that reads more like a soap opera than Austen's dry, controlled irony.
Best The closing telegram is a genuine gut-punch, turning ordinary worry into a real medical emergency in just a few words.
Worst Renfield's speech leans right up against vampire foreshadowing, the dinner is placed on the wrong date, and Seward's reaction to it is far more melodramatic than the calm, clinical man we're shown elsewhere.
Best The interrogation of the widow lays out clear, believable suspicion that keeps the mystery moving.
Worst The gangster's warning note is a cheap, shouty cliché that doesn't match how quietly dangerous he's supposed to be.
Best It hits every required plot point cleanly and clearly, so the chapter is easy to follow and never loses the thread of what needs to happen.
Worst The narration keeps stopping to explain exactly what Edna is feeling and what it all means (a 'fierce, wild thrill of exultation,' an 'unfathomable horizon'), which spells out emotions the original author would have left implied.
Best It delivers every required plot beat clearly and in a sensible sequence, so the mechanics of the chapter are very easy to follow.
Worst The dialogue tips into melodrama that breaks the narrator's dry, understated tone, as when Franklin cries he is 'being hunted... by a pack of brown-faced hounds' and 'in fear of my life.'
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 65.4 | 100 | 65 | 3,101 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 58.4 | 95 | 62 | 2,367 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 54.5 | 100 | 55 | 2,781 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 54.1 | 95 | 57 | 2,929 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 53.4 | 95 | 56 | 3,088 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 52.4 | 100 | 52 | 2,986 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 49.7 | 80 | 62 | 3,112 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 49.3 | 95 | 52 | 2,600 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 49.2 | 95 | 52 | 1,726 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 48.1 | 95 | 51 | 3,235 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Three of ten items landed inside their brief’s word range. Leave It to Psmith and The Sun Also Rises and The War of the Worlds and The Mysterious Affair at Styles and Persuasion and Dracula and The Moonstone ran over by 301 and 181 and 329 and 288 and 386 and 512 and 435 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
The chapter states feelings outright instead of showing them ('I felt cold and completely hollow inside') and strings together too many near-identical stops (Select, Bois, Halles, Crillon) that read like a checklist of a night rather than one shaped scene.
The narration frequently stops to tell the reader exactly what a character is feeling ('He was touched... indicating a nobility of soul he found deeply appealing'), which flattens jokes that should be left for the reader to catch themselves.
The narration keeps stopping to explain exactly what Edna is feeling and what it all means (a 'fierce, wild thrill of exultation,' an 'unfathomable horizon'), which spells out emotions the original author would have left implied.
The big final clue (a scrap of cardboard tied to 'the geometry of shadows') is explained by Poirot in a way that sounds like nonsense rather than a real, teasing mystery clue, so the ending confuses instead of intrigues.
Automated screening results across the ten outputs.