The Standings → Claude Opus 5.5 (high)
Anthropic
high reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at xhigh77.4 medium75.2
Results from run ‘first’: ten items, ten verdicts.
Claude Opus 5.5 (high) scores 75 on craft, 12 points above the field’s 63 and 18 points short of the authors themselves. Its shape differs from the field’s: relatively strong on folding the brief into the story and restraint, relatively weak on momentum and the author’s voice. On the mechanical checks it kept to the brief’s word range on 8 of 10 items and reproduced a 76-word run of the real book verbatim.
The record: 10 items · 10 verdicts · 0 errors · 2,417 words on average · est. generation cost $1.84
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 75. 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 closing telegram is a genuinely gripping reversal that makes you want to turn the page immediately, and it dovetails cleverly with the coerced 29 June letter mentioned in the background.
Worst The final telegram swings very suddenly from confident good news to a medical crisis with almost no earlier hint of danger, so it can land as a jolt rather than a build.
Best Elizabeth's sudden support for Anne's plan is left genuinely ambiguous (the narrator offers several possible, unflattering reasons and shrugs), which feels true to how this author actually handles vanity and self-deception.
Worst A few sentences spell things out a little too plainly, especially the closing paragraph, which reads almost like a tidy list of what went wrong that day rather than a feeling settling over Anne.
Best The solitary swimming scene is genuinely tense and alive, building fear into small triumph without overplaying it.
Worst The closing paragraph spells out Edna's feelings about Robert's remark a little too explicitly instead of just letting the moment sit.
Best The night's route through Paris is mapped out with real care, so the taxi rides and the walk home feel like an actual night happening in an actual city rather than a vague backdrop.
Worst A few lines of dialogue, like the back-and-forth about 'making a gesture,' sound a touch too clever and writerly for characters who are supposed to be talking past each other in short, plain sentences.
Best The wife's plain remark that the thing 'looks as if it had been made' does more work than a dramatic speech would, and it's a sharp, understated character beat.
Worst The chapter sometimes reads like it is quietly checking off a required list of events rather than events growing naturally out of each other.
Best Small worldbuilding touches, like Craven peeling off in the dog-cart while Medlock takes the carriage, and the servant's offhand mention of Martha, make the household feel lived-in and specific.
Worst The narration explains Craven's feelings for him — his face is 'full of trouble' and he seems to be 'looking for something in her face and could not find it' — which softens the mystery the brief and the book both rely on.
Best The mistaken-identity interview, where Lord Emsworth talks roses for a quarter of an hour because he's forgotten why Eve is there, is a lovely piece of character-true comedy that pays off his established absent-mindedness.
Worst Psmith's signature verbal flourish ('Comrade') and grandiloquent excess appear only once, so his voice reads a notch flatter and less distinctive than it should.
Best Small human touches, like the story of the seven-and-sixpence kite and Rosanna's friend Lucy at the Yollands', feel true to life and match the real book's texture closely.
Worst The anonymous warning letter reads like a stock suspense-novel prop, and a line like 'Do not show this letter to any lady' feels too modern and on-the-nose for this period voice.
Best It cleverly circles back to the detail of Lawrence's terrified stare at the mantelpiece from the previous chapter, and the collar-stud left unexplained at the end is a genuinely intriguing hook.
Worst Several key moments (Inglethorp's confession, Poirot's arrival) are summarized after the fact rather than played out as scenes, so parts of the chapter feel reported rather than lived.
Best Thaler's wordless gift of a train ticket and the engraved card reading only 'Lower six is the best berth on the car' is a genuinely chilling, perfectly understated piece of menace in period voice.
Worst It never engages with the source chapter's specific detail that a man and a woman were seen bending over the body, leaving an obvious and inviting thread completely untouched.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| Dracula item 015 · after ch. 5 · Bram Stoker | 82.6 | 100 | 83 | 2,292 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 80.8 | 100 | 81 | 2,285 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 78.4 | 100 | 78 | 1,730 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 76.1 | 100 | 76 | 2,305 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 75.1 | 100 | 75 | 2,573 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 75.0 | 100 | 75 | 2,536 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 73.5 | 100 | 74 | 2,752 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 73.3 | 95 | 77 | 2,883 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 71.5 | 100 | 72 | 2,510 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 62.3 | 100 | 62 | 2,303 |
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 Moonstone ran over by 136 and 83 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
The narration explains Craven's feelings for him — his face is 'full of trouble' and he seems to be 'looking for something in her face and could not find it' — which softens the mystery the brief and the book both rely on.
A few lines of dialogue, like the back-and-forth about 'making a gesture,' sound a touch too clever and writerly for characters who are supposed to be talking past each other in short, plain sentences.
A few sentences spell things out a little too plainly, especially the closing paragraph, which reads almost like a tidy list of what went wrong that day rather than a feeling settling over Anne.
Several key moments (Inglethorp's confession, Poirot's arrival) are summarized after the fact rather than played out as scenes, so parts of the chapter feel reported rather than lived.
Automated screening results across the ten outputs.