The Standings → Muse Spark 1.3 (xhigh)
Meta
xhigh reasoning effort · via OpenCode CLI · judged by Fable 5 and Gemini 3.7 Flash and GPT-5.6 Sol · the setting shown on the standings; also run at medium0.60 high0.58
Results from run ‘first’: ten items, 30 verdicts.
The record: 10 items · 30 verdicts · 0 errors · 2,656 words on average · est. generation cost $0.59
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 (3.73); character the weakest (3.37). 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 Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 0.74 | 0.75 | 0.75 | 0.71 | 2,721 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 0.71 | 0.71 | 0.79 | 0.62 | 2,406 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 0.69 | 0.67 | 0.79 | 0.62 | 2,795 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 0.67 | 0.63 | 0.71 | 0.67 | 2,660 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 0.62 | 0.67 | 0.71 | 0.47 | 2,241 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 0.61 | 0.67 | 0.71 | 0.45 | 2,271 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 0.53 | 0.53 | 0.63 | 0.44 | 2,905 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 0.50 | 0.53 | 0.60 | 0.37 | 3,076 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 0.50 | 0.59 | 0.47 | 0.42 | 3,167 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.48 | 0.64 | 0.45 | 0.34† | 2,314 |
† The widest judge split in the run: Fable 5 0.64 against GPT-5.6 Sol 0.34 on The Sun Also Rises (item 021).
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. The Secret Garden and The Awakening and The War of the Worlds and Persuasion and The Moonstone and Leave It to Psmith ran over by 321 and 995 and 60 and 305 and 276 and 367 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
The closing sentence contradicts the scene it caps — Brett has already gone into her hotel and the taxi has driven off empty, yet the chapter ends with "the taxi carrying Brett" — simultaneously creating an internal continuity error and missing the brief's required end state of having put Brett into a taxi.
The latch-key contradiction is undercooked: Dorcas claims the key hung on its hook all night when the whole household saw Alfred take it the evening before, and Hastings — the narrator who knew this — passes over the discrepancy without a flicker, leaving the chapter's central clue logically unanchored.
To engineer the required end state, the closing porter scene rewrites the umbrella-return we already watched — Eve, who pointedly refused to leave her name and left the note behind, is retroactively said to have taken the note back and given her name — an internal contradiction the reader cannot miss.
The lady in black — a mute background figure in the source — is turned into an oracular mouthpiece whose aphorism (\"Solitude is a prayer that is not always answered\") announces the chapter's theme instead of letting it emerge, the one place the brief's machinery shows through the fabric.
Automated screening results across the ten outputs.