The Standings → GPT‑5.6 Terra
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 · 2,164 words on average · est. generation cost $0.74
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); character the weakest (3.40). 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 Awakening item 016 · after ch. 7 · Kate Chopin | 0.72 | 0.71 | 0.79 | 0.67 | 1,822 |
| Persuasion item 001 · after ch. 1 · Jane Austen | 0.71 | 0.67 | 0.75 | 0.71 | 2,905 |
| The Moonstone item 011 · after ch. 8 · Wilkie Collins | 0.70 | 0.67 | 0.71 | 0.71 | 2,578 |
| The War of the Worlds item 006 · after ch. 1 · H. G. Wells | 0.69 | 0.67 | 0.71 | 0.67 | 2,591 |
| The Secret Garden item 013 · after ch. 2 · Frances Hodgson Burnett | 0.69 | 0.71 | 0.75 | 0.59 | 2,517 |
| Red Harvest item 023 · after ch. 2 · Dashiell Hammett | 0.64 | 0.67 | 0.75 | 0.50† | 2,123 |
| The Mysterious Affair at Styles item 017 · after ch. 3 · Agatha Christie | 0.64 | 0.63 | 0.75 | 0.53 | 2,152 |
| Leave It to Psmith item 022 · after ch. 3 · P. G. Wodehouse | 0.60 | 0.64 | 0.53 | 0.64 | 2,636 |
| Dracula item 015 · after ch. 5 · Bram Stoker | 0.53 | 0.53 | 0.64 | 0.43 | 2,284 |
| The Sun Also Rises item 021 · after ch. 3 · Ernest Hemingway | 0.00 | 0.00 | 0.00 | 0.00 | 28 |
† The widest judge split in the run: Gemini 3.7 Flash 0.75 against GPT-5.6 Sol 0.50 on Red Harvest (item 023).
Words written per item, against each brief’s maximum.
Word count per item vs. brief maximum · run ‘first’
Six of ten items landed inside their brief’s word range. The Awakening and Persuasion and The Secret Garden ran over by 22 and 305 and 117 words respectively.
Each verdict names the chapter’s single worst flaw, with evidence. Quoted verbatim from run ‘first’.
The chapter's biggest event — the reclusive Mr. Craven, who Mrs. Medlock said Mary needn't expect to see, personally meeting the train — is left inert: he says \"So\" and vanishes, and neither Mary's reflection nor Mrs. Medlock's terse reaction registers how extraordinary his presence is, wasting the scene's dramatic charge.
By importing the novel's actual 12 August Budapest letter, the candidate forces a silent three-month time-jump that both strands the required Morris dinner as an awkwardly bolted-on August retrospective and pushes the Renfield scene into forbidden supernatural hinting (\"From no one that you would believe in\").
The required closing image is fumbled: Mike Jackson is on stage at the end — so Psmith is not alone — and Mike's convenient evening appearance at the Drones, paired with Psmith's unexplained knowledge that Eve had been at the Jacksons' house, is a visible contrivance for delivering her name.
The plot machinery is conveniently unexplained — an invented, barely characterized cousin sends Franklin a sealed packet nobody can account for, and my lady's parallel \"I had a letter too\" makes the required prohibition arrive by authorial fiat rather than dramatic necessity.
Automated screening results across the ten outputs.