The Standings → Claude Haiku 4.5 (thinking)
Anthropic
extended thinking · via Claude CLI · judged by Claude Sonnet 5 · the setting shown on the standings; also run at no thinking38.8
Results from run ‘first’: ten items, ten verdicts.
Claude Haiku 4.5 (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 character, relatively weak on restraint and period detail. On the mechanical checks it kept to the brief’s word range on 7 of 10 items and leans on stock phrases more than most.
The record: 10 items · 10 verdicts · 0 errors · 1,997 words on average · est. generation cost $0.54
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 moment Mary steps out onto the dark moor and feels the cold wind on her face is genuinely atmospheric and well observed.
Worst It keeps stopping to explain what Mary is feeling and what Craven's indifference means, in a modern analytical tone, instead of trusting the reader to see it through action, which breaks the old storybook feeling.
Best It hits all four required plot beats clearly and keeps the reader oriented, even when the prose itself is flat.
Worst Anne's big speech comes out as a tidy list of bullet-pointed economies rather than something a timid, overlooked daughter would actually say aloud to her father.
Best It keeps the household's rising unease easy to follow, with Penelope's worry about Rosanna landing as a clear, sympathetic beat.
Worst Franklin's own account of the letter contradicts itself on timing ('reached me in London yesterday' versus the letter itself saying it 'came to my lodgings in town three days ago,' dated the same day as the story's events), and the chapter tells us the stakes directly instead of letting a scene carry them.
Best It hits every required plot point in a clear, sensible order, so a reader can easily follow the telegram, the swim, and the lady in black without getting lost.
Worst The narrator keeps stopping to explain exactly what Edna is feeling and why ("a kind of triumph that was almost fierce in its intensity"), so nothing is left for the reader to notice themselves, and it makes the writing sound modern rather than like 1899.
Best It still delivers every required plot beat clearly and in a sensible order, so the story is easy to follow even though the writing style is off.
Worst It keeps stopping to explain the narrator's inner feelings in overwrought, modern-sounding language instead of just showing what happens, which breaks the spell of the old book's voice.
Best It hits every required plot point cleanly and moves at a brisk, easy-to-follow pace from scene to scene.
Worst It keeps telling us characters' feelings outright (fear, racing hearts, chills) instead of letting their actions show it, and the final exchange between Poirot and Hastings is just confusing rather than intriguingly mysterious.
Best The last scene nicely links Eve to Blandings Castle through gossip, giving Psmith (and the reader) a concrete reason to want to know more about her.
Worst Psmith already greets Eve by name ('Miss Halliday?') hours before the ending scene where he is supposed to just be hearing her name for the first time from Tuppy, so the planned final beat doesn't actually make sense within the chapter's own timeline.
Best The bank scene economically plants a real, nagging mystery (the vanished check) that the rest of the chapter can hang on.
Worst The characters explain their feelings and theories out loud at length instead of the writing showing them through action and clipped dialogue, so it reads like a modern thriller wearing a 1920s costume.
Best The closing telegram has a real small jolt, turning from good news (he left Vienna) to alarm (he never arrived) in one short message.
Worst It breaks the story's own timeline by having Jonathan already safe in a Vienna hotel, recovering from a breakdown, weeks before he could possibly have escaped the castle.
Best It checks off the required plot points cleanly and keeps a subdued, melancholy mood that doesn't tip into melodrama.
Worst It keeps telling the reader what Jake is feeling in flat, explanatory sentences instead of letting the scene show it, and the detour to a stranger's apartment doesn't make logical sense within the story.
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 | 54.0 | 95 | 57 | 2,043 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 48.6 | 95 | 51 | 1,888 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 47.9 | 85 | 56 | 2,633 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 42.0 | 90 | 47 | 1,788 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 39.9 | 100 | 40 | 2,085 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 38.9 | 85 | 46 | 2,795 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 37.8 | 80 | 47 | 2,583 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 36.1 | 95 | 38 | 1,763 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 33.8 | 80 | 42 | 1,639 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 31.9 | 90 | 36 | 753 |
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.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Franklin's own account of the letter contradicts itself on timing ('reached me in London yesterday' versus the letter itself saying it 'came to my lodgings in town three days ago,' dated the same day as the story's events), and the chapter tells us the stakes directly instead of letting a scene carry them.
The narrator keeps stopping to explain exactly what Edna is feeling and why ("a kind of triumph that was almost fierce in its intensity"), so nothing is left for the reader to notice themselves, and it makes the writing sound modern rather than like 1899.
Psmith already greets Eve by name ('Miss Halliday?') hours before the ending scene where he is supposed to just be hearing her name for the first time from Tuppy, so the planned final beat doesn't actually make sense within the chapter's own timeline.
It keeps telling us characters' feelings outright (fear, racing hearts, chills) instead of letting their actions show it, and the final exchange between Poirot and Hastings is just confusing rather than intriguingly mysterious.
Automated screening results across the ten outputs.