Run: 2026-03-03-01KJV0GKA87X4WBD3SNZ56ERKF

Run Details

Duration:
1m 47s
Cost:
$0.001743
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
97.63% Matches word count (details)
12.62% Dialogue to Total Word Ratio (details)
55.1238% 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
They hunched behind the overgrown privet hedge lining Mrs. Henderson’s backyard, the last of the sky-blue birthday balloons bobbing dimly over the wooden deck. The air smelled like crushed Fruit Roll-Ups, bubbled soap, and the faintly metallic tang of spilled lemonade left pooling in a plastic kiddie cup. Molly adjusted her ill-fitting black hoodie, tugging it far enough over her ears to hide her neon pink eyebrow piercing, and gripped a crumpled grocery list she’d used as a stakeout cheat sheet. Bill huddled beside her, fumbling with a cheap plastic knight’s sword he’d swiped from a dollar store checkout rack, prodding at a stray garden gnome instead of casing the deck’s back sliding glass door. “I said I was sorry,” Bill whispered sharply, kicking a crumpled juice box that skittered across the deck tiles. “My boot caught it, okay? I’m not a pro burglar, Molls— I signed up ‘cause you said we’d get to blow party horns.” Molly shot him a look that could curdle cake frosting. “The horns are a distraction. Now grab the black tarp from the canvas tote by your feet and cover your face. Mr. Jenkins next door has eyes like a hawk, and I don’t feel like explaining to the raccoon guy why we’re in cuffs before we pay off our pizza debt.” Bill fumbled the tarp, wrapping it tight around his head like a too-lumpy ghost costume, and tripped over a flamingo lawn ornament, sending a shower of mulch raining onto the deck. They both froze as the sliding glass door clicked open, but it was only Charlie, the six-year-old birthday boy, trotting out clutching a half-eaten cherry lollipop. “Hey!” he yelled, grinning through a missing front tooth. “You’re the face painting ladies! Did you bring the glow sticks like you said?” Molly’s brain sputtered faster than the party’s bubble machine. “We—we forgot them, kiddo! Just grabbing supplies from our car!” Bill leaned in, stage-whispering: “We don’t do face painting.” “Shut up,” Molly snarled under her breath, before turning back to Charlie. “We’ll be right inside if you want to help us set up the glow necklace station?” Charlie whooped and darted back inside, slamming the door behind him. Bill stared at Molly, eyes wide. “We don’t have a glow necklace station.” “Now’s not the time to fact-check,” Molly said, yanking open the tote and grabbing the largest reusable grocery bag they’d brought. “Stuff every wrapped present in here. No glittery bows—those are homemade, and I will personally feed your new space Lego set to the neighborhood geese if you get glitter on the haul.” Bill nodded frantically, grabbing a wobbly stack of wrapped boxes and shoving them into the bag. A crumpled wrapping paper tube clattered to the deck, and Molly froze, listening for footsteps. When no one came, she grabbed a giant stuffed unicorn from the pile, tossing it in after the presents, and gave Bill’s shoulder a sharp shove toward the open door. “Move. And for the love of all things sugary, don’t trip over anything else.”
created_at"2026-03-03T23:28:43.348Z" 3/3/2026, 11:28:43 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency682
moderation_latency(null)
generation_time107251
tokens_prompt77
tokens_completion4640
native_tokens_prompt101
native_tokens_completion4333
native_tokens_completion_images(null)
native_tokens_reasoning3633
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"
usage0.0017433
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"0217725805238042e03d1d5cb4d12864ab68947fc6ea2072af3aa"
is_byokfalse
latency682
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772580523-mxiL1G7aHfhTFxUD9kpi"
upstream_id"0217725805238042e03d1d5cb4d12864ab68947fc6ea2072af3aa"
total_cost0.0017433
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
97.63% Matches word count n/a
neededCleanfalse
words507
12.62% Dialogue to Total Word Ratio
Ratio: 36.43%, Deviation: 6.43%
neededCleanfalse
wordsTotal516
wordsDialogue188
55.1238%