The Standings → Claude Sonnet 5 (high)
Anthropic
high reasoning effort · via Claude CLI · judged by Claude Sonnet 5 · the setting shown on the standings; also run at xhigh60.4 medium60.0 low55.9
Results from run ‘first’: ten items, ten verdicts.
Claude Sonnet 5 (high) scores 65 on craft, 2 points above the field’s 63 and 28 points short of the authors themselves. Its shape differs from the field’s: relatively strong on the author’s voice and restraint, relatively weak on building scenes. On the mechanical checks it kept to the brief’s word range on 7 of 10 items, reproduced a 29-word run of the real book verbatim and leans on stock phrases more than most.
The record: 10 items · 10 verdicts · 0 errors · 2,097 words on average · est. generation cost $0.37
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 65. 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 Mary's stubborn, self-contained personality comes through clearly and consistently, and the chapter ends on a quiet, well-earned note of resolve.
Worst The nighttime moor is described mostly with repeated, generic words like 'blackness' and 'darkness' instead of fresh, specific images.
Best The deadpan comic exchange between Georgette and Zizi at the bal ("He's sick," she explained to Zizi, quite seriously, as though it accounted for everything) captures the book's dry humor well.
Worst Jake's narration keeps explicitly spelling out his feelings ("it left me feeling exactly as though I had been hit, though nobody had touched me at all"), which tells the reader what to feel instead of trusting the scene the way this author does.
Best The gag of Psmith buying back Walderwick's own umbrella from him, initials and all, is a sharp, well-built piece of comic escalation.
Worst The job interview is conducted by Mr. Keeble instead of Lord Emsworth, contradicting what earlier chapters set up, and the scene spells out Keeble's hidden motive a little too plainly.
Best Renfield's exchange with Seward is genuinely unsettling and economical — 'The walls are thin for news, though thick enough for other purposes' — without ever tipping into anything supernatural.
Worst A dating slip breaks the story's own clock: Seward's diary, dated 26 May, treats the dinner as still ahead ('to-morrow night'), while other documents dated the same day and the next morning show the dinner already happened that same night.
Best The lawyer's letter is a neatly oblique, period-plausible piece of evidence that gives Franklin's early arrival a concrete, sinister-sounding cause.
Worst Betteredge decides not to tell Franklin about the Indian jugglers, which undoes the setup's promise that he would tell him that same day and that Franklin would name the Moonstone, so a thread the reader was told to expect just gets dropped.
Best Edna's quiet relief rather than disappointment when the telegram arrives is a small, believable, true-to-character touch.
Worst One sentence in the swimming scene ('A quick vision of death smote her soul') is lifted almost word for word from the real novel's later chapter instead of being the writer's own prose, and right after it the timeline gets muddled — a swim that starts around five o'clock somehow ends with the children already 'long asleep' by the time she gets home.
Best It moves cleanly and efficiently through all the required beats in a single day without ever feeling rushed or confused.
Worst Elizabeth's sudden support for Anne's harsh economy plan comes out of nowhere, with no glimpse of the self-interested reasoning that would make it believable.
Best The widow's refusal to explain herself keeps her guilt or innocence genuinely unresolved instead of wrapping it up too neatly.
Worst The ending trails off into flat, over-explained musing instead of landing on a sharp final image or line.
Best The scene where Dorcas's offhand remark about Baily seeing Alfred slip out the side gate quietly demolishes his alibi is well judged and properly Christie-like in its understatement.
Worst It reads like a checklist of the required plot points ticked off in order, with little of the sly humor or verbal tics that make Poirot and Hastings feel alive, and the person who tips off Poirot is only a vague 'little page-boy' rather than someone the reader actually knows.
Best The moment a young man is burned reaching for the object feels natural and unforced, with the crowd's mixed fear and mockery rendered convincingly.
Worst It gives the story's deliberately nameless narrator a name ('George') and moves the landing site to Horsell Common, breaking both the book's famous anonymity and the brief's instruction to stay near Ottershaw and Chertsey.
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 | 77.0 | 100 | 77 | 2,125 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 71.1 | 95 | 75 | 1,769 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 70.3 | 95 | 74 | 2,938 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 62.7 | 85 | 74 | 1,506 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 59.4 | 95 | 62 | 2,793 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 59.1 | 95 | 62 | 1,420 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 55.8 | 100 | 56 | 2,288 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 52.6 | 90 | 58 | 1,858 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 52.5 | 95 | 55 | 2,163 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 47.4 | 90 | 53 | 2,109 |
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Seven of ten items landed inside their brief’s word range. Leave It to Psmith ran over by 138 words.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
One sentence in the swimming scene ('A quick vision of death smote her soul') is lifted almost word for word from the real novel's later chapter instead of being the writer's own prose, and right after it the timeline gets muddled — a swim that starts around five o'clock somehow ends with the children already 'long asleep' by the time she gets home.
It reads like a checklist of the required plot points ticked off in order, with little of the sly humor or verbal tics that make Poirot and Hastings feel alive, and the person who tips off Poirot is only a vague 'little page-boy' rather than someone the reader actually knows.
Jake's narration keeps explicitly spelling out his feelings ("it left me feeling exactly as though I had been hit, though nobody had touched me at all"), which tells the reader what to feel instead of trusting the scene the way this author does.
Betteredge decides not to tell Franklin about the Indian jugglers, which undoes the setup's promise that he would tell him that same day and that Franklin would name the Moonstone, so a thread the reader was told to expect just gets dropped.
Automated screening results across the ten outputs.