The Standings → Claude Opus 5 (medium)
Anthropic
medium reasoning effort · via Claude CLI · judged by Fable 5 and Gemini 3.7 Flash and GPT-5.6 Sol · not the setting shown on the standings; also run at high0.78
Results from run ‘first’: ten items, 30 verdicts.
The record: 10 items · 30 verdicts · 0 errors · 2,433 words on average · est. generation cost $1.34
Six dimensions, each marked 1–5, averaged over ten items and all judges.
Mean craft mark by dimension · 30 verdicts, run ‘first’
Integration is the strongest dimension (4.47); momentum the weakest (4.00). Hover or focus a bar for the per-judge means.
Each item receives one verdict from each judge; the spread of the dots is the disagreement.
Headline score per item, by judge · run ‘first’
| Item | Headline | Fable 5 | Gemini 3.7 Flash | GPT-5.6 Sol | Words |
|---|---|---|---|---|---|
| The Awakening item 016 · after ch. 7 · Kate Chopin | 0.82 | 0.75 | 0.92 | 0.79 | 1,674 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 0.81 | 0.79 | 1.00 | 0.64† | 2,341 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 0.79 | 0.71 | 0.95 | 0.71 | 2,397 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 0.78 | 0.75 | 0.79 | 0.79 | 2,481 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 0.78 | 0.83 | 0.71 | 0.79 | 2,519 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 0.77 | 0.75 | 0.83 | 0.71 | 2,438 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 0.76 | 0.75 | 0.79 | 0.75 | 2,900 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 0.73 | 0.71 | 0.64 | 0.83 | 2,587 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.72 | 0.75 | 0.79 | 0.62 | 2,315 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 0.70 | 0.64 | 0.83 | 0.64 | 2,675 |
† The widest judge split in the run: Gemini 3.7 Flash 1.00 against GPT-5.6 Sol 0.64 on The Secret Garden (item 013).
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Nine of ten items landed inside their brief’s word range. The Moonstone ran over by 100 words.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Much of the chapter's best material is closely adapted or lifted from Burnett's actual Chapter 3 (the station arrival, the studded oak door, the wind-in-the-corridors speech), so the strongest passages are borrowed rather than invented, and the few original lines — like Mrs. Medlock's snappish \"It sounds like whatever I say it sounds like\" — dip below the period register.
Its strongest passages lean on near-verbatim transcription of Hemingway's actual Chapter 4 (the taxi-route paragraph, the hard-boiled-in-the-daytime reflection), so the chapter's best effects are borrowed rather than invented, and the genuinely original moments occasionally over-state what should stay implicit ("and that she knew it").
The chapter silently elides roughly four hours between the morning-room confrontation and the eleven-o'clock examination (including Poirot's entire off-page interview with Mary), and in doing so also loosens the required closing image, since the shred ends buttoned away in Poirot's pocket rather than lying between the two men.
The chapter introduces severe continuity contradictions with Chapter 1 by placing the fall on the night of the twelfth and having the narrator claim he had not thought of Mars, ignoring both the ten-night launch sequence with its interplanetary transit and the narrator's own telescopic vigil with Ogilvy.
Automated screening results across the ten outputs.