The Standings → Gemini 3.7 Flash (medium)
medium reasoning effort · via Antigravity CLI · judged by Fable 5 and Gemini 3.7 Flash and GPT-5.6 Sol · the setting shown on the standings; also run at high0.56
Results from run ‘first’: ten items, 30 verdicts.
The record: 10 items · 30 verdicts · 0 errors · 3,216 words on average · est. generation cost $0.36
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 (3.57); prose the weakest (3.10). 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 | 0.62 | 0.64 | 0.75 | 0.49 | 2,440 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.62 | 0.67 | 0.75 | 0.46 | 2,760 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 0.60 | 0.68 | 0.64 | 0.49 | 3,844 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 0.60 | 0.63 | 0.71 | 0.45 | 3,650 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 0.57 | 0.64 | 0.75 | 0.32 | 3,619 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 0.57 | 0.55 | 0.75 | 0.40 | 3,317 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 0.55 | 0.60 | 0.75 | 0.30† | 3,357 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 0.53 | 0.51 | 0.67 | 0.42 | 3,713 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 0.50 | 0.58 | 0.58 | 0.32 | 2,104 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 0.49 | 0.59 | 0.53 | 0.34 | 3,351 |
† The widest judge split in the run: Gemini 3.7 Flash 0.75 against GPT-5.6 Sol 0.30 on The Mysterious Affair at Styles (item 017).
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
One of ten items landed inside their brief’s word range. The Sun Also Rises and The Moonstone and The Secret Garden and Leave It to Psmith and The War of the Worlds and The Mysterious Affair at Styles and Persuasion and The Awakening and Red Harvest ran over by 160 and 1,044 and 1,250 and 819 and 717 and 557 and 1,113 and 304 and 751 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Lodging Mary in the West Wing — the wing the source establishes as Mr Craven's forbidden private domain — contradicts the story's central geography, and the surrounding prose compounds it by inflating Burnett's plain style with adjective-heavy padding (\"vast, impenetrable void,\" \"immense, rushing sea of cold air\") that runs the chapter half again over its target length.
The chapter fails to land the required end state — the last time cue is eight o'clock rather than late morning and Poirot pockets the object instead of leaving it between them — and it closes on a vague, fortune-cookie aphorism (\"the pendulum has not yet ceased to swing\") that is portentous mysticism rather than Poirot's precise brand of withheld knowledge.
Both Robert's reported remark ("any man who tried to hold you would find only water slipping through his fingers") and the lady in black's oracular warning ("the sea is very deep, and it has no memory") turn characters into on-the-nose prophetic mouthpieces for the novel's ending, a heavy-handedness foreign to Chopin's method.
The required burn incident is visibly staged rather than earned: the victim is a cartoon strawman ("an active, swaggering sort of young man, who had been loudly boasting") and Ogilvy telegraphs the outcome ("You will be badly scalded!") a paragraph before it happens, so the beat reads as brief-fulfilment instead of story.
Automated screening results across the ten outputs.