The Standings → Gemini 3.8 Flash (medium)
medium reasoning effort · via Antigravity CLI · judged by Claude Sonnet 5 · the setting shown on the standings; also run at high50.6
Results from run ‘first’: ten items, ten verdicts.
Gemini 3.8 Flash (medium) scores 58 on craft, 5 points below the field’s 63 and 35 points short of the authors themselves. Its shape differs from the field’s: relatively strong on period detail and momentum, relatively weak on restraint and folding the brief into the story. On the mechanical checks it kept to the brief’s word range on 0 of 10 items, reproduced a 28-word run of the real book verbatim and leans on stock phrases more than most.
The record: 10 items · 10 verdicts · 0 errors · 3,596 words on average · est. generation cost $0.57
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 58. 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 scene where Jake gives Georgette the money back is sharp and true to her prickly, unsentimental character.
Worst The ending piles on so much scenery (cabbage carts, a sleeping carter, sparks off the cobbles, pink towers) that it slows down and softens the punch the chapter should end on.
Best The spreading rumor and crowd scene is vivid and true to the book's social comedy: 'it was whispered that the fallen star was a volcano of burning sulphur, that it was sinking through to the centre of the earth.'
Worst The prose repeatedly tips into melodrama that Wells's narrator wouldn't use, like calling the half-buried object 'an active, threatening presence, nursing an inextinguishable heat within its monstrous ribs.'
Best The umbrella's physical return to the club lands at the exact moment Walderwick is complaining about it, so the purchase scene clicks together like a well-built mechanism.
Worst The jokes tend to over-explain themselves (spelling out that damp air plays tricks on eyesight, or that Walderwick's hesitation is 'cupidity fighting obstinacy') instead of trusting the reader to get them.
Best The final telegram lands as a genuine gut-punch after a chapter of reassurance, giving real momentum into the next chapter.
Worst The writing keeps telling us exactly how everyone feels (cold sweats, hearts stopping, tears standing on cheeks) instead of trusting the reader, which is much more soap-opera than Stoker's usual understatement.
Best The moment Mary steps out onto the dark, windy moor is vivid and physical, and makes her sudden curiosity about the wild place feel real.
Worst It piles on too many dramatic adjectives and oversells the mysterious noise at the end, so it reads more like a ghost story than the plain, restrained style of the real book.
Best The moment where Dorcas flatly and quietly contradicts Alfred's alibi about the latch-key is well-built and genuinely dramatic, with a nice physical tell in Alfred's reaction.
Worst Large stretches just re-tell things the reader already saw (the whole night's events retold to Poirot, Poirot's appearance described all over again), which drags the pace and reads as summary rather than drama, and the prose leans on stock excitement ('my blood ran cold', 'the adventure had begun') instead of Christie's dry understatement.
Best It builds real, sustained tension around the sealed packet and the ominous warning letter, giving the chapter a strong sense of dread.
Worst It piles on modern spy-thriller melodrama - a sinister unsigned warning letter, men doubling through side streets, a mother who unloads the whole family scandal in one speech - that feels more like a Victorian potboiler pastiche than Wilkie Collins's patient, withholding style.
Best It hits every required plot point in a clean, complete, easy-to-follow sequence, so nothing the brief asked for is missing or muddled.
Worst The characters shout, gasp, and gesture like actors in a melodrama, with constant exclamation points, which feels more like a costume-drama parody than Austen's dry irony.
Best It hits every required story point clearly and in a readable order, so the plot is always easy to follow.
Worst The writing over-explains feelings and pours on dramatic language (like 'blinding ecstasy' and the ominous 'the water is deeper than you think') instead of trusting the reader, which doesn't match the original book's quiet, held-back tone.
Best The physical texture of the bank, hotel, and street is vivid and concrete, giving Personville a strong, grimy sense of place.
Worst The dialogue tips into melodrama and cliché (the widow calling him "a stubborn, fat fool" and warning he'll die "in an alley like Donald"), which breaks the cool, flat tone the story needs.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 73.0 | 100 | 73 | 3,514 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 61.5 | 95 | 65 | 3,143 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 60.8 | 100 | 61 | 4,256 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 55.3 | 95 | 58 | 2,779 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 54.8 | 90 | 61 | 3,512 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 50.8 | 95 | 54 | 4,246 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 50.5 | 95 | 53 | 4,887 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 49.4 | 95 | 52 | 3,798 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 46.3 | 95 | 49 | 2,170 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 43.5 | 80 | 54 | 3,652 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Zero of ten items landed inside their brief’s word range. The Sun Also Rises and The War of the Worlds and Leave It to Psmith and Dracula and The Secret Garden and The Mysterious Affair at Styles and The Moonstone and Persuasion and The Awakening and Red Harvest ran over by 914 and 543 and 1,456 and 179 and 1,112 and 1,446 and 2,087 and 1,198 and 370 and 1,052 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Large stretches just re-tell things the reader already saw (the whole night's events retold to Poirot, Poirot's appearance described all over again), which drags the pace and reads as summary rather than drama, and the prose leans on stock excitement ('my blood ran cold', 'the adventure had begun') instead of Christie's dry understatement.
It piles on modern spy-thriller melodrama - a sinister unsigned warning letter, men doubling through side streets, a mother who unloads the whole family scandal in one speech - that feels more like a Victorian potboiler pastiche than Wilkie Collins's patient, withholding style.
The writing over-explains feelings and pours on dramatic language (like 'blinding ecstasy' and the ominous 'the water is deeper than you think') instead of trusting the reader, which doesn't match the original book's quiet, held-back tone.
The writing keeps telling us exactly how everyone feels (cold sweats, hearts stopping, tears standing on cheeks) instead of trusting the reader, which is much more soap-opera than Stoker's usual understatement.
Automated screening results across the ten outputs.