Run: 2026-03-03-01KJTZFGJAJKW2C3N0J7N3PESN

Run Details

Duration:
3m 33s
Cost:
$0.003143
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
81.27% Matches word count (details)
33.38% Dialogue to Total Word Ratio (details)
57.3260% 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
The dented white cargo van idled across the street from the Split Oak cul-de-sac, where a neon pink bounce house billowed in the late August breeze and the high-pitched shriek of a dozen 7-year-olds spilled over the picket fence. Bill hunched in the passenger seat, a half-melted chocolate chip cookie crumbing onto his khakis, his eyes locked on the front porch where a stack of wrapped gifts teetered under a plastic Elsa centerpiece. He clutched a crumpled checklist scrawled with Molly’s sharp, looping rules: Gifts ONLY. No face paint. No unauthorized bounce house rides. “You sure the piñata crack is our window?” Bill asked, prodding a crumb off his knee. “What if a parent spots two people hauling garbage bags full of stuffed animals and board books out of a kid’s party?” Molly twisted a roll of neon pink duct tape between her fingers, her van’s peeling “Party Rentals” stencil glinting in the hot sun. “Last month I helped a pastor load a basket of baptism onesies into my trunk—parents at these parties are too busy chasing sugar-crazed toddlers to notice a couple of helpful guests. The piñata splits in exactly two minutes; everyone’s heads will be up watching candy rain. We dart across the lawn, slip through the side fence gate, grab the stack of gifts, and bolt back to the van before the birthday kid even misses his toy truck.” Bill’s Adam’s apple bobbed. “What about the birthday boy? My little sister cried for three days when her stuffed bear got stolen from her 6th birthday party.” Molly snickered, tossing him a black contractor’s garbage bag. He fumbled it, spilling cookie crumbs onto the van’s crusted, peanut butter-stained floor mat. “Relax. We’ll leave a stack of free lollipop coupons taped to the empty spot where his big gift was. He’ll think it’s a parting favor from the party planner. Priority one: no tiny human meltdowns.” Bill scanned his checklist again, his ballpoint pen hovering over the “LOLLIPOP COUPONS” line he’d scribbled that morning in a panic. “You remembered the coupons? I totally blanked on the coupons.” “Relax, I’ve got ’em,” Molly said, digging into her frayed backpack and tossing a stack of neon pink cat-themed coupons across the seat. She checked her analog watch, jaw tightening. “Thirty seconds. The piñata guy just got the flimsy wooden bat. Don’t trip over the bounce house stakes when you run—last heist I tripped over a jump rope and face-planted into a pile of glittery party favors. Still had glitter in my hair for a week.” A loud, cracking thrum cut through the van’s open window, followed by a roar of screaming, cheering kids. “Okay! Okay, go time!” Bill yelped, scrambling to yank his garbage bag closed. Molly slammed the van’s passenger door, already halfway across the lawn before the words finished leaving his mouth. She waved over her shoulder at Bill, who stumbled over a garden hose and nearly dropped his bag mid-stride, as the first handfuls of multicolored candy began to rain down on the crowd below the bounce house.
created_at"2026-03-03T23:10:39.19Z" 3/3/2026, 11:10:39 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency3113
moderation_latency(null)
generation_time212600
tokens_prompt77
tokens_completion8143
native_tokens_prompt101
native_tokens_completion7833
native_tokens_completion_images(null)
native_tokens_reasoning7129
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"
usage0.0031433
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"0217725794395992e03d1d5cb4d12864ab68947fc6ea2075073ee"
is_byokfalse
latency3113
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772579439-Z2CNVAXGWSv5c4rSgudY"
upstream_id"0217725794395992e03d1d5cb4d12864ab68947fc6ea2075073ee"
total_cost0.0031433
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
81.27% Matches word count n/a
neededCleanfalse
words512
33.38% Dialogue to Total Word Ratio
Ratio: 45.32%, Deviation: 4.68%
neededCleanfalse
wordsTotal523
wordsDialogue237
57.3260%