Run: 2026-03-03-01KJTXZWQV83YAX48GXWEM4SSP

Run Details

Duration:
2m 5s
Cost:
$0.002007
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
0.00% Matches word count (details)
23.26% Dialogue to Total Word Ratio (details)
11.6307% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 50% 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
They huddle behind a dented plastic wading pool abandoned on the curb, the kind that usually holds rainwater and neighborhood frogs. Molly’s $3 garage-sale binoculars fog up at the edges as she scans the backyard, where a creaky piñata hangs from an oak branch, its paper mache dinosaur tail already split open to spill candy. The air smells like melted vanilla frosting and cherry Kool-Aid, and every few seconds a shriek of delighted rage rips through the picket fence—either over a stolen lollipop or a kid who took a shoulder to the face from an overzealous party guest. Bill twists a crumpled roll of duct tape between his sweaty palms, his Yankees baseball cap already drawing sideways glares from the kids playing cornhole in the driveway; he’d forgotten this suburb’s youth league bans Yankee gear, a fact Molly had pointed out three times, so he’d stuffed a women’s floral kerchief in his pocket to cover it, though it kept slipping down his nose. “ You sure this is a smart play?” Bill mumbles around the kerchief, yanking it back into place. “ We’re not stealing from kids,” Molly says, lowering the binoculars to narrow her eyes at him. “We’re stealing from their helicopter parents. Those presents? They’re gonna get regifted to a cousin’s hamster next quarter, or left in the back of a closet until they get moldy. This is just redirecting surplus festive goods.” “ I saw a kid clutching a Millennium Falcon Lego set,” Bill says, voice drooping. “That’s $120 on Facebook Marketplace.” “ Exactly,” Molly says, tapping his duffel bag at his feet. “You’re here to load up on shiny wrapped stuff. I’m handling the distraction.” “ Wait, your face paint ‘skills’ got my niece banned from her church’s craft night,” Bill says, jerking his chin at the face paint kit Molly’s clutching. “Last time you turned her unicorn horn purple instead of pink. She cried for two hours.” “ I watched three TikTok tutorials overnight,” Molly replies, holding up a stencil of a sparkly llama. “It’s a classic. The moms here will eat it up. Now, the code to the back gate is 1234— the mom wrote it on a fridge sticky note, I swiped it while she was bragging about her tumbler party favor.” A tiny toddler in a frayed princess dress bolts around the side of the house, chasing a monarch butterfly, and skids to a halt three feet from their hiding spot. Bill freezes, binoculars clattering to the concrete. Molly yanks the binoculars back, shoves a dandelion head into his mouth to muffle his sputter, and grins so wide it looks painful. The toddler blinks, then bursts into wailing tears. “ Honey, are you okay?” a woman’s voice calls from the backyard. “ Just a butterfly emergency!” Molly yells back, waving wildly. “The monarch got away!” She waits until the woman waves back before yanking the dandelion out of Bill’s mouth. Bill sputters, spitting out a fluffy tuft of dandelion fluff and a tiny caterpillar. “I just ate a backyard caterpillar! Do you think they have booster shots?!” “ Relax,” Molly snorts, grabbing her face paint kit and starting toward the gate. “The caterpillar was way more traumatized. Now go— the piñata just broke, everyone’s diving for candy. Skip the homemade cookie swag, stick to the wrapped presents. Move fast, and don’t trip over the garden gnome. It’s definitely glued to the stepping stone.”
created_at"2026-03-03T22:44:38.793Z" 3/3/2026, 10:44:38 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency342
moderation_latency(null)
generation_time125154
tokens_prompt77
tokens_completion5441
native_tokens_prompt101
native_tokens_completion4991
native_tokens_completion_images(null)
native_tokens_reasoning4210
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"
usage0.0020065
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"021772577878925682bfa727eaa8ae907bb4f408e14b63de73087"
is_byokfalse
latency342
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772577878-sxBX7pd4EPXp8TgdUq48"
upstream_id"021772577878925682bfa727eaa8ae907bb4f408e14b63de73087"
total_cost0.0020065
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
0.00% Matches word count n/a
neededCleanfalse
words572
23.26% Dialogue to Total Word Ratio
Ratio: 44.60%, Deviation: 5.40%
neededCleanfalse
wordsTotal574
wordsDialogue256
11.6307%