The Standings → GPT‑5.5
OpenAI
xhigh reasoning effort · via Codex CLI · judged by Claude Sonnet 5
Results from run ‘first’: ten items, ten verdicts.
GPT‑5.5 scores 66 on craft, 3 points above the field’s 63 and 26 points short of the authors themselves. Its shape differs from the field’s: relatively strong on restraint, relatively weak on period detail and building scenes. On the mechanical checks it kept to the brief’s word range on 3 of 10 items.
The record: 10 items · 10 verdicts · 0 errors · 2,098 words on average · est. generation cost $2.28
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 characters stay consistent and recognisable throughout, especially Sir Walter's vanity and self-pity and Elizabeth's pride, and the barb 'Anne's plan is a very young lady's plan, though Anne is not so very young either' is a nicely judged character moment.
Worst Several key passages, especially the two economy plans and Anne's speech, are described in vague, list-like terms rather than being rendered with specific concrete detail, so they read more like a summary than a scene actually happening.
Best Having Eve accidentally sit on Lord Emsworth's pince-nez during the interview is a clever, character-true way to make the meeting go wrong while staying warm and funny.
Worst The chapter ends by having a phone call summarize the day's events instead of showing them, which feels like a report rather than a scene.
Best The final telegram (fevered, nuns, 'serious but hopeful') is a genuinely gripping, concretely detailed jolt that reorients the whole chapter's anxious searching into real crisis.
Worst A couple of Seward's diary passages explain his own conclusions too plainly ("This may explain it," "I must be more guarded in my own speech") instead of letting the reader infer them.
Best The dialogue is lively and well-observed, especially Ogilvy's exasperated arguing and the crowd's joking, which captures a believable village-holiday mood around something uncanny.
Worst The falling star is made to land during the very walk the source chapter says happens while the missile is still ten million miles away, which contradicts the timeline it is continuing from.
Best Alfred's alibi is punctured with a sharp, homely piece of evidence — Dorcas quoting the egg-girl's gossip that Denby's family was away — which feels exactly like how Christie plants a contradiction.
Worst The investigation scene moves through the required beats efficiently but stays a little generic, without enough vivid physical detail to make the room search feel special.
Best It delivers every required plot point cleanly, especially the bank scene and Thaler's note, and closes on a nicely understated image of the Op alone wondering where the money went.
Worst The widow's interrogation runs on too long with too many flat one-word denials, so it starts to feel like a checklist of questions rather than a real conversation between two people.
Best It is clean, easy to follow, and never trips over itself, delivering everything asked for without clutter.
Worst It rushes through the required story beats one after another so the chapter feels more like a checklist being ticked off than a scene the reader is living through.
Best The final exchange with Georgette back at the dance hall is warm and funny and sounds like her.
Worst Several plot points, especially the mention of the rich count, feel dropped in and then abandoned rather than growing out of the conversation.
Best It hits every required plot point cleanly and without padding, so the story moves along efficiently.
Worst Everything happens very fast with little sensory detail, so the chapter reads like a summary of events rather than a scene you're living through.
Best It hits every required beat cleanly and lands exactly on the required ending without padding or digression.
Worst Almost the whole chapter is delivered as quick summary rather than scenes you can watch unfold, so it reads like a list of plot points rather than a lived afternoon.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| Persuasion item 001 · after ch. 1 · Jane Austen | 78.5 | 100 | 78 | 2,296 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 76.0 | 100 | 76 | 2,916 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 73.4 | 95 | 77 | 3,509 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 71.4 | 95 | 75 | 2,692 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 68.5 | 95 | 72 | 2,654 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 63.6 | 95 | 67 | 2,448 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 60.0 | 100 | 60 | 1,620 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 59.1 | 100 | 59 | 1,463 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 51.2 | 100 | 51 | 814 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 47.4 | 100 | 47 | 570 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Three of ten items landed inside their brief’s word range. Leave It to Psmith and Dracula and The War of the Worlds ran over by 116 and 909 and 92 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Several key passages, especially the two economy plans and Anne's speech, are described in vague, list-like terms rather than being rendered with specific concrete detail, so they read more like a summary than a scene actually happening.
The falling star is made to land during the very walk the source chapter says happens while the missile is still ten million miles away, which contradicts the timeline it is continuing from.
A couple of Seward's diary passages explain his own conclusions too plainly ("This may explain it," "I must be more guarded in my own speech") instead of letting the reader infer them.
The widow's interrogation runs on too long with too many flat one-word denials, so it starts to feel like a checklist of questions rather than a real conversation between two people.
Automated screening results across the ten outputs.