The Standings → GPT‑5.6 Sol
OpenAI
medium reasoning effort · via Codex CLI · judged by Fable 5 and Gemini 3.7 Flash and GPT-5.6 Sol
Results from run ‘first’: ten items, 30 verdicts.
The record: 10 items · 30 verdicts · 0 errors · 2,235 words on average · est. generation cost $1.42
Six dimensions, each marked 1–5, averaged over ten items and all judges.
Mean craft mark by dimension · 30 verdicts, run ‘first’
Voice is the strongest dimension (4.10); momentum the weakest (3.83). 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 |
|---|---|---|---|---|---|
| Dracula item 015 · after ch. 5 · Bram Stoker | 0.82 | 0.71 | 0.96 | 0.79 | 2,320 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 0.81 | 0.71 | 0.96 | 0.75† | 2,643 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 0.78 | 0.71 | 0.92 | 0.71 | 2,551 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 0.75 | 0.75 | 0.75 | 0.75 | 2,448 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 0.75 | 0.75 | 0.75 | 0.75 | 2,176 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 0.74 | 0.67 | 0.75 | 0.79 | 2,196 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 0.71 | 0.71 | 0.75 | 0.67 | 2,206 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.71 | 0.71 | 0.71 | 0.71 | 2,109 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 0.69 | 0.75 | 0.75 | 0.57 | 1,502 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 0.69 | 0.71 | 0.75 | 0.59 | 2,199 |
† The widest judge split in the run: Gemini 3.7 Flash 0.96 against Fable 5 0.71 on Persuasion (item 001).
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. Persuasion ran over by 43 words.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Lady Verinder's prohibition scene is the one visible seam: her demand arrives within a minute of Franklin's welcome with its motive flatly withheld ("I have reasons for this which I shall not explain"), so the beat reads as an item being ticked rather than something the scene earned.
The chapter plants a glaring timeline hole — the widow was told her husband \"had been hurt\" twenty minutes before he was shot — and the Op, established in the source as the man who nailed those exact times, never remarks on it, so it reads as authorial oversight rather than clue.
Robert's remark about "a voice no one else can hear" is too neat a theme statement, and by being quoted verbatim three times — on the walk, in Adèle's repetition, and again in the closing paragraph — it over-underlines a motif Chopin would have trusted the reader to carry.
Elizabeth's surprising support — the brief's boldest divergence — is immediately deflated by a paragraph of narrated motive ("She could fancy it spoken of as Miss Elliot's plan"), explaining away the one moment that should have been left to unsettle the reader.
Automated screening results across the ten outputs.