The Standings → GPT‑6 Sol (xhigh)
OpenAI
xhigh reasoning effort · via Codex CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at high63.8 medium62.9
Results from run ‘first’: ten items, ten verdicts.
GPT‑6 Sol (xhigh) scores 62 on craft, 1 points below the field’s 63 and 31 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 period detail and building scenes. 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 · 2,297 words on average · est. generation cost $1.06
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 62. 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 It hits every required story beat clearly and efficiently, so the plot is always easy to follow.
Worst Much of the chapter tells us what Mary is thinking and feeling instead of dramatizing it through action and dialogue, which makes the prose read flatter than the original book's style.
Best The re-creation of the dim candlelit room by closing the curtains, and the quiet, specific way Baily flatly contradicts Alfred, are the kind of concrete deductive touches that feel true to Poirot's method.
Worst Poirot comes across as oddly muted and Hastings's narration stays even-keeled throughout, so the chapter never quite catches fire the way a discovery of murder should.
Best The unscripted side-trip to the murder alley, counting bullet scars and sightlines, feels like real detective legwork and grounds the chapter in physical fact.
Worst The interview with Mrs. Willsson collapses into a long string of one-line question-and-answer volleys that reads like a police transcript instead of a scene between two people.
Best The chapter is cleanly and clearly plotted, hitting every required story beat without confusion about who said what or why.
Worst Too much of the confrontation is delivered as flat plot summary ('Sir Walter declared the plan impossible') rather than played out in the room, so the big moments don't land with much force.
Best It delivers every required plot point with clean, unambiguous staging, especially Penelope's direct report about Rosanna going to Cobb's Hole, so nothing is left for the reader to puzzle over.
Worst Too much of the chapter is told in flat summary (an afternoon passing, servants coming and going) instead of played out as a scene, so it feels reported rather than lived.
Best The crowd scene and the moment the young man burns his hand are staged with clear, believable escalation, step by step.
Worst The sentences are clean and competent but feel more like careful modern pastiche than Wells's own rolling, digressive way of writing.
Best It stays quiet and doesn't over-explain, letting the swim and Robert's remark land without spelling out what they mean.
Worst The writing is careful but plain, missing the lyrical, socially observant texture that makes Chopin's sentences distinctive.
Best It hits every required plot point cleanly and efficiently, with nothing wasted and no scene that drags.
Worst The dialogue and narration are flat and businesslike where the real book would be rich with comic exaggeration, so it reads like a competent summary of Wodehouse rather than Wodehouse himself.
Best It hits every required story beat cleanly and unobtrusively, including a nice small callback to Georgette's bad-teeth smile from the source chapter.
Worst The sentences are clean but flat and interchangeable with generic period fiction, missing Hemingway's dry wit and the particular rhythm of his dialogue.
Best The closing telegram is a genuine gut-punch twist that makes you want to re-read everything that came before.
Worst It quietly moves Quincey's dinner to a different night than the one already fixed in the letters just before it, and mostly tells us what happened rather than showing it.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 73.2 | 100 | 73 | 2,218 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 66.9 | 100 | 67 | 2,582 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 66.1 | 100 | 66 | 2,426 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 63.7 | 100 | 64 | 2,457 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 61.9 | 100 | 62 | 2,738 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 61.4 | 100 | 61 | 2,212 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 59.5 | 100 | 60 | 1,639 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 56.9 | 100 | 57 | 2,299 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 54.5 | 100 | 55 | 2,191 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 50.7 | 90 | 56 | 2,210 |
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’.
The dialogue and narration are flat and businesslike where the real book would be rich with comic exaggeration, so it reads like a competent summary of Wodehouse rather than Wodehouse himself.
Too much of the confrontation is delivered as flat plot summary ('Sir Walter declared the plan impossible') rather than played out in the room, so the big moments don't land with much force.
Much of the chapter tells us what Mary is thinking and feeling instead of dramatizing it through action and dialogue, which makes the prose read flatter than the original book's style.
The interview with Mrs. Willsson collapses into a long string of one-line question-and-answer volleys that reads like a police transcript instead of a scene between two people.
Automated screening results across the ten outputs.