The Standings → GPT‑6 Sol (high)
OpenAI
high reasoning effort · via Codex CLI · judged by Claude Sonnet 5 · the setting shown on the standings; also run at medium62.9 xhigh61.5
Results from run ‘first’: ten items, ten verdicts.
GPT‑6 Sol (high) scores 66 on craft, 3 points above the field’s 63 and 27 points short of the authors themselves. Its shape differs from the field’s: relatively strong on restraint, relatively weak on momentum and the author’s voice. 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 · 2,313 words on average · est. generation cost $0.90
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 66. 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 dialogue is the strongest element: Robert's line about Edna and the exchange with Adèle sound genuinely like this teasing, slightly vain young man rather than an authorial mouthpiece.
Worst The descriptive writing is functional but plain in places, missing the richer sensory texture the setting could offer, especially in the siesta and swim passages.
Best The widow's interview is built out of short, wary question-and-answer exchanges that let her evasiveness show through instead of being explained.
Worst A couple of lines, like night having "filled the window," reach for a poetic effect this flat, unshowy narrator wouldn't use.
Best The plotting is clean and disciplined, especially the way Dorcas's specific, concrete testimony catches Alfred in a provable lie about the latch-key.
Worst Poirot comes across as a generic, subdued detective rather than the vain, excitable Belgian of the books — almost none of his characteristic speech mannerisms survive.
Best The small, oblique exchange about Jake offering his coat to Brett captures unspoken feeling well.
Worst The last line baldly states the required ending almost like a checklist item, which makes the close feel flat and unearned.
Best The ink-bottle accident during the library interview is a clean, visually specific piece of slapstick that grows naturally out of the scene.
Worst Several key comic moments, like the umbrella purchase and the porter's exchange, are rushed through in a few flat lines instead of being played out as a scene, so the humor doesn't land.
Best The confrontation scene is clear, well-organized, and easy to follow, with a nicely timed comic beat when Sir Walter forbids the word 'tenant.'
Worst The chapter marches through the required plot points so tidily that it feels more like a checklist being ticked off than a scene unfolding on its own logic.
Best Every plot point the brief asked for is delivered cleanly and is easy to follow, with no confusion about what happened or why.
Worst The chapter ends by simply listing off the three required facts in a row, so it reads like a checklist being ticked off rather than a scene that was actually lived through.
Best The moment Mary climbs out onto the dark moor and looks up to see stars through a break in the clouds is quiet and well-judged, capturing the strangeness of the place without overplaying it.
Worst Mr. Craven sits silently in the carriage for the entire long ride home, which feels like an odd, wasted use of him rather than something a real recluse would plausibly do.
Best It stages every required beat cleanly and calmly, especially the burn and the wife's departure, without ever tipping into melodrama.
Worst The writing is careful and correct but often flat, reading more like a modern retelling than Wells's own cadence and wit.
Best The final telegram is a genuine gut-punch that completely upends the reader's expectations and creates real urgency for the next chapter.
Worst With eleven short, similarly flat documents, the chapter reads like a checklist of required beats being ticked off rather than a lived correspondence, and it quietly shifts the fixed dinner date by a day.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| The Awakening item 016 · after ch. 7 · Kate Chopin | 76.8 | 100 | 77 | 1,724 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 74.1 | 100 | 74 | 2,245 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 71.8 | 100 | 72 | 2,373 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 65.5 | 100 | 66 | 2,056 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 64.1 | 95 | 68 | 2,416 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 62.5 | 100 | 62 | 2,599 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 60.0 | 100 | 60 | 2,561 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 59.1 | 100 | 59 | 2,446 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 58.1 | 100 | 58 | 2,471 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 45.9 | 75 | 61 | 2,242 |
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. The Secret Garden ran over by 46 words.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
With eleven short, similarly flat documents, the chapter reads like a checklist of required beats being ticked off rather than a lived correspondence, and it quietly shifts the fixed dinner date by a day.
Several key comic moments, like the umbrella purchase and the porter's exchange, are rushed through in a few flat lines instead of being played out as a scene, so the humor doesn't land.
The chapter ends by simply listing off the three required facts in a row, so it reads like a checklist being ticked off rather than a scene that was actually lived through.
Mr. Craven sits silently in the carriage for the entire long ride home, which feels like an odd, wasted use of him rather than something a real recluse would plausibly do.
Automated screening results across the ten outputs.