The Standings → Claude Opus 5.5 (xhigh)
Anthropic
xhigh reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · the setting shown on the standings; also run at medium75.2 high74.9
Results from run ‘first’: ten items, ten verdicts.
Claude Opus 5.5 (xhigh) scores 77 on craft, 14 points above the field’s 63 and 16 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. On the mechanical checks it kept to the brief’s word range on 8 of 10 items.
The record: 10 items · 10 verdicts · 0 errors · 2,293 words on average · est. generation cost $5.12
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 77. 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 moor scene is vividly sensory (glowing sheep's eyes, wind like a pushing hand), and the footman's Yorkshire is glossed in parentheses exactly the way the original author explains dialect words, which nails the voice.
Worst A few images and sentence constructions are more polished and novelistic than the plain, matter-of-fact style of the real book.
Best The concrete period details—the lawyer's green bag, the unheated forcing-houses, Elizabeth's silent arithmetic about her own age—ground the argument in exact, believable texture.
Worst Splitting the letter into a separate short scene after the library meeting breaks the momentum built up by the tenant-word confrontation, so the chapter ends on a slightly quieter note than it could.
Best The invented detail that Alfred claims it rained overnight, only for Dorcas to flatly deny any rain fell, is a small, quietly planted clue that lands exactly like a genuine piece of period detective fiction.
Worst During Poirot's long room search the chapter switches into a quick list of actions ('He took measurements, and lay flat upon the floor... He examined the washstand') instead of staying in scene, so a couple of hours go by as summary rather than drama.
Best The final page is quietly eerie and well controlled, ending on a bare, unexplained image (the empty back door, the struck clock) that makes you want to keep reading without the narrator spelling out why you should worry.
Worst The warning letter is signed only 'A Well-Wisher' and stays vague about who is watching Franklin or why, so the danger feels a bit generic instead of sharply real.
Best The seed-catalogue mix-up with Lord Emsworth is a genuinely clever, specifically Wodehousian misunderstanding, and the phone call from Mike Jackson delivers the required name-reveal with real elegance.
Worst Psmith drops his trademark 'Comrade' address when talking to Walderwick (though he uses it for Jackson later), making his voice slightly inconsistent within the same chapter.
Best The last telegram genuinely upends what the reader was just told (a fever that is "nothing" becomes someone "gravely ill"), which gives the ending real bite and pull.
Worst The chapter jumps from 5 June straight to 10 July with nothing in between, so the middle goes slack and the reader loses a month of the Jonathan worry the chapter is supposed to be building.
Best It weaves the bicycle-riding and moral-philosophy details from the source chapter into the opening so naturally that it reads like an organic continuation rather than a checklist.
Worst The wife's line 'I do not like it. I cannot tell you why' is a stock foreboding cliche that tells us she's uneasy instead of showing it the way the rest of the chapter otherwise does.
Best The physical sensation of the swim and the quiet, believable ending on the dark porch feel true to who Edna is.
Worst It spells out the meaning of the swimming scene a little too plainly, telling the reader what to feel instead of trusting them to notice it.
Best Thaler's wordless warning — a timetable with one train circled and his bare calling card — is a genuinely chilling, show-don't-tell touch that fits the character's established menace.
Worst The closing paragraph spells out the Op's chain of reasoning about the check a bit too fully, telling the reader conclusions it could have let them draw themselves.
Best Jake's line about not knowing why he wants to go back for the envelope ('It seemed like something to do that was simple') captures the book's trick of showing feeling through action instead of explaining it.
Worst The ending plays it safe and doesn't hit as hard emotionally as it could, so the ride home along the river feels pleasant rather than truly haunting.
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 | 85.6 | 100 | 86 | 2,419 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 81.8 | 100 | 82 | 2,297 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 80.6 | 100 | 81 | 2,484 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 79.9 | 100 | 80 | 2,668 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 79.8 | 100 | 80 | 2,362 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 77.5 | 100 | 78 | 2,361 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 74.4 | 100 | 74 | 2,638 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 74.4 | 100 | 74 | 1,668 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 74.1 | 100 | 74 | 2,042 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 66.4 | 100 | 66 | 1,987 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Eight of ten items landed inside their brief’s word range. The Secret Garden and The War of the Worlds ran over by 19 and 38 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
During Poirot's long room search the chapter switches into a quick list of actions ('He took measurements, and lay flat upon the floor... He examined the washstand') instead of staying in scene, so a couple of hours go by as summary rather than drama.
Splitting the letter into a separate short scene after the library meeting breaks the momentum built up by the tenant-word confrontation, so the chapter ends on a slightly quieter note than it could.
The chapter jumps from 5 June straight to 10 July with nothing in between, so the middle goes slack and the reader loses a month of the Jonathan worry the chapter is supposed to be building.
The wife's line 'I do not like it. I cannot tell you why' is a stock foreboding cliche that tells us she's uneasy instead of showing it the way the rest of the chapter otherwise does.
Automated screening results across the ten outputs.