The Standings → GPT‑6.1 Sol (xhigh)
OpenAI
xhigh reasoning effort · via Codex CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at medium66.1 high63.0
Results from run ‘first’: ten items, ten verdicts.
GPT‑6.1 Sol (xhigh) scores 64 on craft, 1 points above the field’s 63 and 28 points short of the authors themselves. Its shape differs from the field’s: relatively strong on restraint and folding the brief into the story, relatively weak on momentum and the author’s voice. On the mechanical checks it kept to the brief’s word range on 10 of 10 items and is unusually free of stock phrases.
The record: 10 items · 10 verdicts · 0 errors · 2,326 words on average · est. generation cost $1.10
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 64. 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 closing telegram delivers a clean, satisfying reversal — the reassuring letter turns out to be about a different man entirely — which sharpens rather than resolves the suspense.
Worst Quincey's letter reads as a polite, generic Englishman rather than the slangy Texan established in the source material, and the Renfield scene drifts into a childhood-room description that doesn't earn its place.
Best It hits every required plot beat cleanly and keeps the numbers and logic of the retrenchment plans easy to follow.
Worst The dialogue mostly states characters' positions and numbers plainly, so it reads more like a well-organized business meeting than an Austen scene alive with irony.
Best The prose is clean and controlled, with a few genuinely sharp comic lines (the sun 'examining Shaftesbury Avenue with the air of a visitor brought to the wrong address') and a nicely staged physical comedy set piece with the spilled ink.
Worst The jokes and voice are pleasant but land a bit plainer and more contemporary than Wodehouse's actual style, and the chapter doesn't connect to the book's bigger plot threads (the poet, the necklace, Uncle Keeble's errand) — it reads like a self-contained side story.
Best It is disciplined and clear, working through every required beat smoothly without padding or overwrought emotion.
Worst The writing is careful and correct but a little flat, so the scene never quite catches fire the way the original book's prose does.
Best The moment Mary climbs out onto the moor is tightly controlled and physically specific, with a real sense of the ground and wind under her feet.
Worst The writing is clipped and efficient in a way that feels more like modern minimalist prose than Burnett's warmer, more discursive Victorian narrating voice.
Best The return to Georgette is quietly well observed — the detail of her rubbing one foot with the other and her flat remark that the young men 'all want to leave when they see somebody they know' gives her a life of her own in just a few lines.
Worst Brett loses almost all of her distinctive clipped British slang ('chap,' 'rather,' 'priceless') and sounds like a generic melancholy woman rather than Lady Ashley, while the chapter drifts through too many half-scenes (two cafés, a shoe window, a sleeping man, a sweeping man) without any one of them building real pressure.
Best The alibi lie is set up cleanly and paid off with a sharp, concrete contradiction from Dorcas, giving the chapter a real working puzzle instead of just atmosphere.
Worst Poirot barely sounds like Poirot — almost none of his French exclamations, vanity, or little lectures come through, so he reads as a generic careful detective rather than the specific character established in the source chapter.
Best The legwork is careful and believable, especially the extra stop canvassing the neighbors on Hurricane Street, which feels like real detective work.
Worst Too much of the chapter is people answering rapid-fire questions in a row, so it reads more like a police transcript than a scene with people in it.
Best It is clean, clear, and gets every required event on the page without confusion or wasted motion.
Worst It reads like a checklist of required plot points delivered mostly through short question-and-answer dialogue, missing Betteredge's rambling, joke-cracking way of telling a story.
Best It handles the quiet moments well — Edna's first swim and the lady in black's first words are understated and let the reader feel the weight without the prose pointing at it.
Worst The sentences are so short and plain, one after another, that it reads like a modern minimalist writer rather than the rich, flowing 1899 voice of the original book.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| Dracula item 015 · after ch. 5 · Bram Stoker | 70.9 | 95 | 75 | 2,215 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 69.6 | 100 | 70 | 2,468 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 67.9 | 100 | 68 | 2,395 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 67.2 | 95 | 71 | 2,481 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 65.2 | 100 | 65 | 2,274 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 64.9 | 100 | 65 | 2,264 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 62.0 | 95 | 65 | 2,466 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 58.4 | 100 | 58 | 2,374 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 52.7 | 95 | 56 | 2,584 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 51.7 | 100 | 52 | 1,742 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Ten of ten items landed inside their brief’s word range.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Brett loses almost all of her distinctive clipped British slang ('chap,' 'rather,' 'priceless') and sounds like a generic melancholy woman rather than Lady Ashley, while the chapter drifts through too many half-scenes (two cafés, a shoe window, a sleeping man, a sweeping man) without any one of them building real pressure.
The jokes and voice are pleasant but land a bit plainer and more contemporary than Wodehouse's actual style, and the chapter doesn't connect to the book's bigger plot threads (the poet, the necklace, Uncle Keeble's errand) — it reads like a self-contained side story.
Poirot barely sounds like Poirot — almost none of his French exclamations, vanity, or little lectures come through, so he reads as a generic careful detective rather than the specific character established in the source chapter.
Quincey's letter reads as a polite, generic Englishman rather than the slangy Texan established in the source material, and the Renfield scene drifts into a childhood-room description that doesn't earn its place.
Automated screening results across the ten outputs.