NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKRWNXMXC3QGFEV986DD28Q
Run Details
Model:
Stealth: Aurora Alpha
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.9s
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
The night before the birthday bash, Molly and Bill crouched behind folding chairs in the community center’s hallway. Neon streamers clung to the ceiling, and the faint smell of frosting lingered, making the mission sound absurdly festive. Molly, a former magician’s assistant, whispered a plan while twirling a cheap plastic wand, scanning the makeshift gift table piled with brightly wrapped parcels. Bill, a retired accountant turned cat‑ burglar, consulted a crumpled schematic of the venue, noting the fire‑exit door that led directly to the children’s play area. They imagined themselves as stealthy elves, slipping past giggling toddlers and dodging “Happy Birthday” chants. Their banter was peppered with absurd metaphors, and each step was rehearsed with the seriousness of a bank robbery, only to be undercut by the ridiculousness of stealing candy‑filled toys and glittery crayons. As midnight approached, they checked their gear: a sack of empty gift bags, lock‑picking tools, and oversized clown shoes for distraction. The absurdity made them grin, and the thrill felt like a mischievous birthday wish granted. They felt unstoppable, like kids with secret candy in. Molly: Back door, quiet. Bill: Disable lights, grab gifts quickly. Molly: Watch kids, stay hidden now. Bill: We’re ghosts silently.
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
51.8871%
Dialogue to Total Word Ratio
Ratio: 1.00%, Deviation: 9.00%
neededClean
false
wordsTotal
200
wordsDialogue
2
75.9435%