The Standings → Muse Spark 1.3 (high)
Meta
high reasoning effort · via OpenCode 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 xhigh0.60 medium0.60
Results from run ‘first’: ten items, 30 verdicts.
The record: 10 items · 30 verdicts · 0 errors · 2,642 words on average · est. generation cost $0.47
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 (3.70); character the weakest (3.33). 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 | 0.76 | 0.75 | 0.75 | 0.79 | 2,526 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 0.71 | 0.75 | 0.75 | 0.62 | 2,201 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 0.59 | 0.59 | 0.75 | 0.44 | 2,756 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 0.57 | 0.63 | 0.47 | 0.60 | 3,291 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 0.57 | 0.59 | 0.71 | 0.39† | 2,088 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 0.55 | 0.54 | 0.71 | 0.40 | 2,619 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 0.54 | 0.71 | 0.47 | 0.42 | 3,054 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 0.53 | 0.57 | 0.64 | 0.40 | 2,398 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 0.49 | 0.53 | 0.59 | 0.35 | 3,279 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.44 | 0.59 | 0.40 | 0.34 | 2,205 |
† The widest judge split in the run: Gemini 3.7 Flash 0.71 against GPT-5.6 Sol 0.39 on The Awakening (item 016).
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 War of the Worlds and The Awakening and Persuasion and The Moonstone and Leave It to Psmith ran over by 126 and 691 and 288 and 19 and 254 and 479 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
The chapter's chronology collapses under inspection: Arthur's proposal drifts across three different dates against the source's fixed 24 May, and Jonathan is placed in Buda-Pesth and then London while his journal has him imprisoned in the castle through 30 June, so the climactic telegram lands as contradiction rather than twist.
The moor stop is visibly engineered to serve the brief: a nine-year-old in mourning slips out of her guardian's carriage into a dark, windy moor at night and neither Mr. Craven nor the adults meaningfully react ('Mr. Craven said nothing. He did not turn his head.'), which strains plausibility even for these cold characters.
The chapter renders almost everything in indirect summary with barely a line of direct speech, and at the required beats it lifts the brief's own wording nearly verbatim (\"spoke aloud, and in company\", \"still entirely unsettled\"), so the mandated moments read as announced checklist items rather than dramatized scenes.
The chapter tells the same information three times over — in the scenes, in the Op's explanatory summaries (\"she was scared and... she lied badly\"), and again verbatim in the wire — so its middle stretch recaps rather than advances, and the interiority spells out inferences Hammett's Op would leave to the reader.
Automated screening results across the ten outputs.