The Standings → Claude Haiku 4.5 (no thinking)
Anthropic
no extended thinking · via Claude CLI · judged by Claude Sonnet 5 · not the setting shown on the standings; also run at thinking41.1
Results from run ‘first’: ten items, ten verdicts.
Claude Haiku 4.5 (no thinking) scores 46 on craft, 17 points below the field’s 63 and 47 points short of the authors themselves. Its shape differs from the field’s: relatively strong on momentum and sentence-level prose, relatively weak on restraint and folding the brief into the story. On the mechanical checks it kept to the brief’s word range on 4 of 10 items and leans on stock phrases more than most.
The record: 10 items · 10 verdicts · 0 errors · 1,874 words on average · est. generation cost $0.13
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 46. 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 bank scene is brisk and functional, and the kid-tailing-then-note device for Thaler's warning is a workable, unfussy way to deliver his message off-page.
Worst The writing keeps stopping to spell out what things mean (what the note 'meant', what the ending 'thought about') instead of trusting the reader, which flattens the hard-boiled tone into something closer to a paraphrase of it.
Best It hits all the required plot points clearly and keeps the story moving without confusion.
Worst The anonymous warning letter is overwrought and vague in a way that doesn't match the calm, everyday tone of the original, and a random mention of 'trouble at the jeweller's in York' is dropped in and never explained.
Best The moment Mary stands alone on the moor and feels small against its vastness is simply and effectively rendered.
Worst It replaces the required 'wind' explanation with an unexplained night cry that reads like a child crying, which is exactly the kind of moment the brief said to avoid.
Best The three-way tension between Ogilvy's scientific certainty, the inspector's doubts, and the narrator's unease keeps the central question - ordinary stone or something stranger - visible throughout.
Worst The narrator bicycles off to Woking, breaking the rule that he stay near Ottershaw and Chertsey, and several lines read like modern narration rather than 1898 prose.
Best It moves briskly and clearly from the money argument to Mary's letter without getting bogged down.
Worst It gives the house-letting idea to Anne and then has Sir Walter scold Mr Shepherd for saying a word Shepherd never actually said, which makes a key scene not add up.
Best The moment where the maid catches Alfred Inglethorp in a lie about the latch-key and his night away is sharp, clear, and dramatically effective.
Worst Near the end, Poirot explains his whole theory about motive and a suspicious detail out loud in plain language, which makes him sound like he's narrating the plot rather than being the careful, tight-lipped detective from the books.
Best The swimming scene itself reads as a believable, nervous first success, with a nice quiet exultation afterward.
Worst It keeps explaining how Edna feels in modern therapy-speak instead of letting her actions and the dialogue show it, and it skips the actual walk home so Robert's remark only ever arrives secondhand.
Best Psmith's mock-solemn speech talking Walderwick into selling his own umbrella has real comic rhythm and sounds like the character.
Worst The umbrella's whereabouts contradict themselves (Eve hands it to a porter in a taxi, then later is said to collect it from a cafe), and the interview is held by an invented stand-in named Waterbury instead of Lord Emsworth, who the story has already said would do the interviewing.
Best It hits the required plot points cleanly and gives the Georgette return scene real tension with the rival young man.
Worst Jake keeps explaining his feelings in plain analytical sentences instead of letting the reader infer them, which breaks the clipped, withholding style the rest of the book uses.
Best The Renfield scene has a clean, unsettling build through plain repetition: 'She is well? You would tell me if she were not well?'
Worst The ending telegram just confirms the nervous-illness news already given in the first letter, so instead of reversing what the reader expects it merely repeats it with added detail.
Headline, compliance and craft for each chapter, 0–100.
| Item | Headline | Compliance | Craft | Words |
|---|---|---|---|---|
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 44.3 | 95 | 47 | 1,651 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 42.2 | 85 | 50 | 2,407 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 40.8 | 75 | 54 | 1,393 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 39.8 | 80 | 50 | 1,884 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 39.4 | 90 | 44 | 2,068 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 39.2 | 80 | 49 | 1,815 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 38.7 | 90 | 43 | 1,493 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 37.9 | 90 | 42 | 2,873 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 36.2 | 85 | 43 | 1,531 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 30.0 | 70 | 43 | 1,622 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Four of ten items landed inside their brief’s word range. Leave It to Psmith ran over by 73 words.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
The umbrella's whereabouts contradict themselves (Eve hands it to a porter in a taxi, then later is said to collect it from a cafe), and the interview is held by an invented stand-in named Waterbury instead of Lord Emsworth, who the story has already said would do the interviewing.
Near the end, Poirot explains his whole theory about motive and a suspicious detail out loud in plain language, which makes him sound like he's narrating the plot rather than being the careful, tight-lipped detective from the books.
The writing keeps stopping to spell out what things mean (what the note 'meant', what the ending 'thought about') instead of trusting the reader, which flattens the hard-boiled tone into something closer to a paraphrase of it.
The anonymous warning letter is overwrought and vague in a way that doesn't match the calm, everyday tone of the original, and a random mention of 'trouble at the jeweller's in York' is dropped in and never explained.
Automated screening results across the ten outputs.