The Standings → GPT‑5.6 Sol
OpenAI
medium reasoning effort · via Codex CLI · judged by Claude Sonnet 5
Results from run ‘first’: ten items, ten verdicts.
GPT‑5.6 Sol scores 68 on craft, 5 points above the field’s 63 and 25 points short of the authors themselves. Its shape differs from the field’s: relatively strong on momentum, relatively weak on folding the brief into the story. On the mechanical checks it kept to the brief’s word range on 9 of 10 items and is unusually free of stock phrases.
The record: 10 items · 10 verdicts · 0 errors · 2,235 words on average · est. generation cost $1.42
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 68. 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 small comic touches — the ruined dinner 'fit for building purposes,' the running joke about the seven-and-sixpence — keep Betteredge warm and funny even as the plot tightens.
Worst The anonymous warning letter reads like a generic thriller note rather than something grounded in this book's world, so it feels thinner than the prose around it.
Best The crowd itself is vividly alive, with rumor multiplying by the minute (silver, poison, soldiers, a treasure-ship from the stars), which captures Wells's satirical eye for how a small town processes the impossible.
Worst Some of the dialogue, especially the clipped back-and-forth about the 'knocking' sound ('It was knocking.' 'Stones settling.' 'It knocked three times.'), reads more like a modern scripted exchange than Wells's continuous retrospective prose, which briefly breaks the illusion of period voice.
Best The dialogue is clipped and efficient in the Hammett manner, especially the bank interrogation and the anonymous phone threat, and small touches like the widow's practiced calm ('she had said it quietly to herself often enough to have it perfect') show real character insight without explaining it.
Worst The widow's confession comes out too smoothly and completely for someone who supposedly ran from a murder scene hours earlier, so the mystery gets tidied up faster than it should.
Best The small, tight exchange 'Will you mind?' 'Why should I?' 'I don't know.' 'Go ahead.' lets Jake's jealousy show entirely through clipped dialogue instead of explanation.
Worst Long stretches of dialogue collapse into rapid one-line volleys with almost no narration or physical business between them, so several scenes read like a transcript rather than a staged encounter.
Best The chapter hits every required story beat cleanly and in a clear, easy-to-follow sequence.
Worst Mr. Craven exchanges several lines directly with Mary at the station ('You are tired,' 'I was asleep'), which makes the cold, self-absorbed recluse from the source material seem oddly attentive and talkative.
Best Small concrete objects carry real weight — the bay horses 'admired by Lord L—— only last autumn' and the mirrors in the shut-up eastern rooms make Sir Walter's vanity feel physical and specific rather than merely asserted.
Worst Anne's big speech to the family reads like an itemized budget memo ('We ought to sell the carriage horses... to reduce the servants... to receive no company... to buy nothing...') rather than something a diffident young woman would actually say aloud.
Best The Piccadilly scene where Eve tries to trap Psmith into admitting he gave her the umbrella is snappy, playful dialogue that sounds like real back-and-forth banter.
Worst Lord Emsworth is suddenly given a fixation on pigs, which clashes with everything we've been told about him being a flowers-and-garden man, so it feels like the wrong character.
Best The fraudulent-letter twist is a genuinely clever, well-engineered final beat that delivers real shock in the closing telegram.
Worst Several passages lapse into modern-sounding aphorism ('silences which humiliate, and silences which strengthen') that sit oddly next to Stoker's plainer Victorian cadences.
Best It delivers all four required story beats cleanly and lands exactly on the required closing image without straining.
Worst After the beach scene, most of the chapter is told in quick summary instead of played out as scenes, so the middle sags.
Best The moment where Dorcas catches Alfred in a lie about a hole in his coat pocket is crisp, well-placed, and lands with real quiet tension.
Worst It invents a mysterious telegram that supposedly brings Evelyn Howard back to the village within an hour of the death, which doesn't make timeline sense and is never explained or followed up.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 75.4 | 100 | 75 | 2,448 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 72.9 | 100 | 73 | 2,551 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 69.9 | 100 | 70 | 2,196 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 69.0 | 100 | 69 | 2,109 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 67.6 | 95 | 71 | 2,176 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 66.2 | 100 | 66 | 2,643 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 64.5 | 95 | 68 | 2,206 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 63.5 | 95 | 67 | 2,320 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 61.1 | 100 | 61 | 1,502 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 57.2 | 95 | 60 | 2,199 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Nine of ten items landed inside their brief’s word range. Persuasion ran over by 43 words.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Some of the dialogue, especially the clipped back-and-forth about the 'knocking' sound ('It was knocking.' 'Stones settling.' 'It knocked three times.'), reads more like a modern scripted exchange than Wells's continuous retrospective prose, which briefly breaks the illusion of period voice.
Anne's big speech to the family reads like an itemized budget memo ('We ought to sell the carriage horses... to reduce the servants... to receive no company... to buy nothing...') rather than something a diffident young woman would actually say aloud.
Mr. Craven exchanges several lines directly with Mary at the station ('You are tired,' 'I was asleep'), which makes the cold, self-absorbed recluse from the source material seem oddly attentive and talkative.
Long stretches of dialogue collapse into rapid one-line volleys with almost no narration or physical business between them, so several scenes read like a transcript rather than a staged encounter.
Automated screening results across the ten outputs.