The Standings → Gemini 3.7 Flash
high reasoning effort · via Antigravity 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 medium0.56
Results from run ‘first’: ten items, 30 verdicts.
The record: 10 items · 30 verdicts · 0 errors · 3,371 words on average · est. generation cost $0.92
Six dimensions, each marked 1–5, averaged over ten items and all judges.
Mean craft mark by dimension · 30 verdicts, run ‘first’
Momentum is the strongest dimension (3.57); prose the weakest (3.07). 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 Moonstone item 011 · after ch. 8 · Wilkie Collins | 0.62 | 0.59 | 0.75 | 0.53 | 3,762 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 0.61 | 0.63 | 0.75 | 0.46 | 3,087 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 0.60 | 0.64 | 0.71 | 0.46 | 3,755 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 0.57 | 0.59 | 0.75 | 0.38 | 3,255 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 0.57 | 0.58 | 0.71 | 0.42 | 2,637 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 0.55 | 0.51 | 0.75 | 0.40 | 3,455 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.54 | 0.55 | 0.71 | 0.36 | 3,382 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 0.54 | 0.53 | 0.75 | 0.34† | 4,363 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 0.51 | 0.59 | 0.55 | 0.40 | 4,204 |
| The Awakening item 016 · after ch. 7 · Kate Chopin | 0.47 | 0.51 | 0.58 | 0.32 | 1,808 |
† The widest judge split in the run: Gemini 3.7 Flash 0.75 against GPT-5.6 Sol 0.34 on Red Harvest (item 023).
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Zero of ten items landed inside their brief’s word range. The Moonstone and Dracula and Leave It to Psmith and The War of the Worlds and Persuasion and The Mysterious Affair at Styles and The Sun Also Rises and Red Harvest and The Secret Garden and The Awakening ran over by 962 and 487 and 955 and 655 and 37 and 655 and 782 and 1,763 and 1,804 and 8 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
Seward's 28 May entry over-explains and melodramatizes the Renfield mystery — \"The question struck me like a physical blow... The blood seemed to rush from my head to my heart\" — telling the reader how uncanny it is instead of letting the question land, and in doing so pushes right up against the ban on supernatural hinting.
Lady Verinder's unmotivated omniscience — she somehow already knows Franklin has come "on a mission ... connected with the past" — exists only to trigger the required prohibition scene, and it visibly breaks both her characterisation and the letter's own secrecy instruction.
Chronic overwriting — nearly every noun carries two or three adjectives (\"a sudden glare of extraordinary brilliance\", \"a glowing trail of luminous vapor... like a luminous scar\") — pads the chapter far past the brief and dilutes Wells's economical, understated dread.
The chapter pads and over-explains every effect — nearly twice the brief's length, with the closing passage spelling out Mary's deduction ('It was a living, moving sound, and Mrs. Medlock had lied to her') that Burnett would have trusted the reader to make.
Automated screening results across the ten outputs.