Run: 2026-03-03-01KJTY6R7VCJAR4BK33AGZAH03

Run Details

Duration:
2m 60s
Cost:
$0.002800
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
1.04% Matches word count (details)
86.67% Dialogue to Total Word Ratio (details)
43.8515% 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
Dusk bleeded soft pink over the tree-lined suburban street, and the only sounds besides crickets and distant lawnmowers were the high, reedy cheers from a backyard tent strung with lopsided helium balloons and a tinny, looping “Baby Shark” track. Bill hunched behind a row of azalea bushes, his thrifted fanny pack digging into his hip, while Molly picked at a loose shingle on the neighbor’s fence, her scuffed white sneakers smudging clover into green smudges. “Molls,” Bill muttered, not tearing his eyes from the tent flap, “last week you said we’d heist a downtown food truck. Now we’re crashing a kindergarten birthday party? For wrapped presents?” Molly slipped a stolen pack of sour gummy bears from their beat-up Ford’s glove compartment into her hoodie pocket, her grin sharp and lazy. “Food trucks have security cameras and dudes with spatulas that will actually fight you. This is daycare heist, lite: all the good presents are stacked by the punch bowl, no guards just glitter-covered kids and a mom glued to TikTok.” “But the parents!” Bill yelped as a toddler in a dinosaur costume darted past the bushes, flattening himself against the hedge until the kid was out of sight. “Someone’s always watching at these things!” “Pfft, I scoped this at noon,” Molly said, tucking a frayed black bandana—once part of a 2019 Halloween pirate costume—over her mouth like a makeshift mask. “The birthday mom’s got a sunflower sunhat, scrolling Reels so hard she didn’t notice her kid put ketchup on the grill. The dad’s burning hot dogs and arguing with the neighbor about the playlist. No one’s looking.” Bill fumbled with his jacket zipper, hands slick with sweat. “What if we get caught? They’ll call the cops, and we’ll have a record, and then we can’t take that pizza delivery job we applied for last week.” “Relax,” Molly said, already creeping toward the tent, steps silent except for the crinkle of her hoodie drawstring. “We’re just borrowing some gifts. I brought a backup distraction, too.” “Backup distraction?” Bill whispered, stumbling after her, azalea clippings sticking to his collar. Molly nodded at a tiny princess who’d stumbled out of the tent, clutching a sippy cup, and froze mid-step when she spotted them. “Hey there, cutie!” she called, waving too wide. “We’re here for the face painting station! We lost our brushes!” The princess tilted her head, pointing at Molly’s bandana. “You’re a pirate.” “Bad pirate,” Molly amended, wincing. “Emergency backup pirate. Wanna help us find the holographic glitter glue?” Bill grabbed Molly’s arm, voice tight. “Molly, we are not recruiting a five-year-old accomplice.” “Please,” Molly scoffed, already pointing at the stack of brightly wrapped boxes by the snack table. “You grab those, I’ll grab the big unicorn gift bag by the punch bowl. If anyone asks, we’re the late entertainers who bailed on the party.” Bill stared at the stacks, mouth dry. “What if one of them’s coal? Or boring kids’ socks?” Molly snickered, already hauling a giant wrapped box toward the backyard gate. “Socks sell on Facebook Marketplace for twice what you pay for them. C’mon, before the dad notices his hot dogs are ash.”
created_at"2026-03-03T22:48:23.561Z" 3/3/2026, 10:48:23 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency761
moderation_latency(null)
generation_time179762
tokens_prompt77
tokens_completion7417
native_tokens_prompt101
native_tokens_completion6974
native_tokens_completion_images(null)
native_tokens_reasoning6223
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"
usage0.0027997
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"021772578103990e9db803be2da2d1fb0370cddd09ba5d6b85d5c"
is_byokfalse
latency761
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772578103-5uvvklgiYaGGOKNfnaaI"
upstream_id"021772578103990e9db803be2da2d1fb0370cddd09ba5d6b85d5c"
total_cost0.0027997
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
1.04% Matches word count n/a
neededCleanfalse
words526
86.67% Dialogue to Total Word Ratio
Ratio: 48.31%, Deviation: 1.69%
neededCleanfalse
wordsTotal532
wordsDialogue257
43.8515%