Run: 2026-03-03-01KJTYMSN0BGCT8VVE9H92P8FV

Run Details

Duration:
5m 18s
Cost:
$0.004489
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
0.49% Matches word count (details)
23.75% Dialogue to Total Word Ratio (details)
12.1194% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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

AI
Molly and Bill huddled behind a scraggly pink azalea bush two houses down from the Johnson family’s annual strawberry Shortcake birthday bash, the air thick with cloying cotton candy fumes, melted popsicle drips, and the high-pitched cackle of sugar-fueled toddlers chasing each other with streamers. Molly adjusted a lopsided Minnie Mouse ear headband she’d snagged from a dollar party bin, smearing a tiny bit of glitter on her cheek as she tightened the plastic band, her gaze locked on the towering stack of wrapped gifts propped against the back porch rail. The pile gleamed with neon pink, blue, and yellow wrapping paper, a crinkly Batman-shaped bag peeking out atop a floppy neon-pink unicorn box, and she’d already mentally tallied each item before Bill’s signature pre-heist jitters kicked in. “Molls, we can’t do this,” Bill whispered, wiping sweat from his greasy bangs with the back of his hand, his scuffed sneakers digging divots into the grass. “Last time you got me stealing something, I got stuck with snack duty forever. I don’t need more trouble.” Molly rolled her eyes, flipping open the crumpled McDonald’s napkin she’d scrawled her heist checklist on, a crumb of breakfast sandwich still stuck to the edge. “Calm down. The caterer’s inside for soda, parents are herding crashed toddlers, the clown’s eating cake. We’re grabbing the presents, no one will notice.” Bill fumbled with the unicorn-patterned canvas tote slung over his shoulder, pulling at a loose thread on its glittery horn print, and nearly dropped a pair of disposable latex gloves he’d stashed inside. “What if the balloon clown spots us? His sword-shaped balloon looks like it could pop a lung if he swung it the wrong way.” “The clown can’t see straight through the frosting crumbs stuck to his cheek,” Molly muttered, already creeping out from behind the bush, tiptoeing along the shadowed fence line as her headband slipped down over one eye. “Stay low, and don’t stop to pet the golden retriever napping by the porch—he’s a professional sniffer, and I don’t feel explaining our little heist to a bunch of confused suburban parents.” They slipped through the propped-open side gate, Bill nearly tripping over a stack of crinkly plastic lawn chairs before Molly yelped and yanked him forward, her sneakers crunching on a sugary stray confetti egg. The stack of presents was only ten feet away now, and Molly could see the crinkled Walmart price tag still stuck to the side of a Toy Story-themed gift bag. Bill snatched open his unicorn tote, his hands shaking so hard a loose thread flapped in the warm breeze, when a sudden high-pitched giggle made them both freeze mid-step. A tiny toddler in a frilly princess dress popped out from behind the deflated bounce house, staring at them with a mouth full of pink lollipop and wide, confused eyes.
created_at"2026-03-03T22:56:03.757Z" 3/3/2026, 10:56:03 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency655
moderation_latency(null)
generation_time317816
tokens_prompt77
tokens_completion11867
native_tokens_prompt101
native_tokens_completion11198
native_tokens_completion_images(null)
native_tokens_reasoning10552
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0044893
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"021772578564170904c389cfd819598df3df498c1c52189a26ecf"
is_byokfalse
latency655
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772578563-IFReEDbcxCDczyR9gxKs"
upstream_id"021772578564170904c389cfd819598df3df498c1c52189a26ecf"
total_cost0.0044893
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
0.49% Matches word count n/a
neededCleanfalse
words473
23.75% Dialogue to Total Word Ratio
Ratio: 24.64%, Deviation: 5.36%
neededCleanfalse
wordsTotal483
wordsDialogue119
12.1194%