The Standings → GPT‑5.6 Terra
OpenAI
medium reasoning effort · via Codex CLI · judged by Claude Sonnet 5
Results from run ‘first’: ten items, ten verdicts.
GPT‑5.6 Terra scores 56 on craft, 7 points below the field’s 63 and 37 points short of the authors themselves. Its shape differs from the field’s: relatively strong on restraint and the author’s voice, relatively weak on folding the brief into the story and period detail. On the mechanical checks it kept to the brief’s word range on 6 of 10 items.
The record: 10 items · 10 verdicts · 0 errors · 2,164 words on average · est. generation cost $0.74
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 56. 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 Small character touches land well, like the aside that a plate-room key "has its feelings, like a human creature" and the quiet final image of rereading the same page of Robinson Crusoe without taking in a word.
Worst It drops the Indian fortune-telling thread from the previous chapter entirely, so the letter and packet feel like a new, disconnected mystery rather than the payoff the story had been building toward.
Best The scene where Renfield calmly and unpromptedly asks about Miss Westenra is genuinely unsettling and feels true to the character he becomes later in the book.
Worst It makes a big unexplained jump forward in time and drops in a couple of overly sentimental lines (like 'my darling, my darling, hold fast') that feel soapier than the rest of the writing.
Best The hushed, wary exchange between Mrs Medlock and Mr Craven at the station convincingly shows how the whole household is afraid of him.
Worst Several passages state Mary's feelings and motives directly instead of dramatizing them, and some exchanges (with the driver, with Thomas) run on with procedural detail that slows the scene.
Best The bickering between Sir Walter and Shepherd over small words like "united" and "flowers" builds a nice, petty comic escalation that suits Sir Walter's vanity.
Worst It drops in Mrs Clay as an already-established intimate friend of Elizabeth's ("Mrs Clay herself would be shocked at it"), a character never introduced anywhere in the material the reader has been given, which breaks continuity and confuses the story so far.
Best The description of the object's impact — the tearing roar, the sudden light, windows flashing and a horse plunging in its shafts — is immediately dramatic and pulls the reader in from the first page.
Worst Several exchanges have characters state the story's themes out loud instead of letting readers infer them, which makes the dialogue feel more like a modern debate than restrained period prose.
Best The mixed-up luncheon bill during Lord Emsworth's interview is a clever, plausible bit of business that fits his absent-mindedness and lets Baxter's officiousness land well.
Worst Much of the dialogue, especially the umbrella confrontation, is clipped one-line question-and-answer that reads more like a script than the flowing, ornate sentences this author favors.
Best The small mystery-clue touches are nicely judged, especially the moment Poirot notices the mantelpiece clock has simply run down rather than stopped, which plants a clue without over-explaining it.
Worst The big confrontation with Inglethorp happens with Poirot already standing right there watching, which flattens the scene into a group Q&A instead of building suspense, and several moments (like Hastings' 'This maddened me') just state feelings instead of showing them.
Best The interrogation-style dialogue (with Hargis at the bank and with the widow in the hotel room) has a genuinely convincing clipped, evasive rhythm that's close to Hammett's real interview scenes.
Worst The widow's account of finding "a crowd" and "police" already on the scene before she reaches the body contradicts the source's account that the mystery man and woman vanished before anyone else arrived.
Best The quiet, unresolved ending on the dark gallery matches the restrained, wistful note the real book tends to end its chapters on.
Worst It reads like a checklist of required plot points being ticked off one by one rather than a scene that grows on its own, and it briefly contradicts the previous chapter by saying Adèle barely needed Robert's arm right after she'd been shown leaning on it from cramp.
Best It is at least honest that it won't attempt to fully mimic Hemingway's style, though that honesty is useless when a chapter was actually requested.
Worst It never actually writes the chapter at all — it's just a message declining the task, so there is no story to read.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 68.6 | 100 | 69 | 2,578 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 63.7 | 100 | 64 | 2,284 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 62.9 | 95 | 66 | 2,517 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 61.5 | 95 | 65 | 2,905 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 59.1 | 90 | 66 | 2,591 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 56.0 | 90 | 62 | 2,636 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 52.5 | 95 | 55 | 2,152 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 51.2 | 85 | 60 | 2,123 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 50.1 | 90 | 56 | 1,822 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.0 | 70 | 0 | 28 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Six of ten items landed inside their brief’s word range. The Secret Garden and Persuasion and The Awakening ran over by 117 and 305 and 22 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
The big confrontation with Inglethorp happens with Poirot already standing right there watching, which flattens the scene into a group Q&A instead of building suspense, and several moments (like Hastings' 'This maddened me') just state feelings instead of showing them.
It reads like a checklist of required plot points being ticked off one by one rather than a scene that grows on its own, and it briefly contradicts the previous chapter by saying Adèle barely needed Robert's arm right after she'd been shown leaning on it from cramp.
It drops in Mrs Clay as an already-established intimate friend of Elizabeth's ("Mrs Clay herself would be shocked at it"), a character never introduced anywhere in the material the reader has been given, which breaks continuity and confuses the story so far.
The widow's account of finding "a crowd" and "police" already on the scene before she reaches the body contradicts the source's account that the mystery man and woman vanished before anyone else arrived.
Automated screening results across the ten outputs.