NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8A979QF4YTEGTSMM6Z6AT
Run Details
Model:
ByteDance Seed 1.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
14.4s
Cost:
$0.000516
Provider:
Seed
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
46.8287%
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
Messages
Meta
AI
The party was running late. Not that that mattered—rain sluiced down, turning the street into a mirror, but the house at 123 Maple still glowed with fairy lights. A minion-shaped piñata hung by the porch, its paper eyes staring like betrayed goldfish. Bill pressed his forehead to the rain-streaked glass, squinting at the living room. “The cake’s a unicorn. Glitter everywhere. Karen’s niece is crying because she thinks the ice cream truck is lost.” Molly leaned against the yew bush, popping a lollipop she’d swiped from a nearby gas station. “Crying kids are part of the decor. Last week, a kid tried to bite my ankle during a heist at a baby shower. Customer service said it was ‘developmental.’” She adjusted her hat—featuring a cartoon owl that wouldn’t stay on—and nodded at a window. “See that? The presents are stacked by the TV. Lego sets, stuffed bunnies, a tablet with *Frozen* on it. Karen’s husband spent three grand. Idiot. Figured he’d skimp on security once he saw the piñata.” Bill fumbled with a lockpick, his hands slick. “What if they have security? I saw a mom take a photo of the goodie bags. Swore up and down they had ‘organic crayons.’” Molly snickered. “Organic crayons. Cute. You think that’s the only security? The real guard’s a golden retriever who thinks he’s a detective. He’s napping by the filing cabinet. Stupid dog. Stole my sandwich at the library last year.” Bill paused, lockpick hovering. “Why a kids’ party? Robbing a candy store’s easier. No glitter. No…’ He gestured vaguely at the house. ‘…no tiny superhero capes that probably cost more than a gold watch.” Molly sneered. “Candy store’s for rookies. Kids’ parties? The presents are wrapped in uncut paper, no serial numbers. And the parents are too busy kissing the host’s ass to check a single gift. Last year, I took a Lego set that was worth three months’ rent. The kid didn’t even notice till his mom cried in the bathroom. Best part? The dad tried to frame the piñata. ‘He must’ve slipped!’” She cackled. “Candy store don’t buy you therapy.” Bill muttered something about “carbohydrates and car seats” but started jiggling the ribbon. “Hurry. I don’t want to be here when the ice cream truck shows up. My allergy to artificial vanilla is… *intense*.” Molly pushed off the bush, grinning. “Relax. We’ll be in and out before the dog finishes his dreamland racket. And if the unicorn cake’s still intact? We’ll take a *bitem*. For research.” Bill grunted, the ribbon twisting loose. “Research my ass. You just want sprinkles.” “Better than therapy,” Molly said, pulling a utility knife from her boot. The glass slide door slid open with a hiss. Behind them, the rain mellowed, and somewhere, a kid shrieked—probably the ice cream truck arrived. Molly winked. “Let’s steal us a *dream*.” They melted into the house, the piñata creaking like a museum guard.
created_at
"2026-02-20T19:27:06.484Z"
2/20/2026, 7:27:06 PM
model
"bytedance-seed/seed-1.6-flash-20250625"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
580
moderation_latency
(null)
generation_time
13691
tokens_prompt
77
tokens_completion
1792
native_tokens_prompt
149
native_tokens_completion
1683
native_tokens_completion_images
(null)
native_tokens_reasoning
955
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.000516075
router
(null)
provider_responses
0
endpoint_id
"e01a1227-001b-44d4-a376-90850668fa84"
id
"0217716156267282e03d1d5cb4d12864ab68947fc6ea2078e2fae"
is_byok
false
latency
421
model_permaslug
"bytedance-seed/seed-1.6-flash-20250625"
provider_name
"Seed"
status
200
api_type
"completions"
id
"gen-1771615626-x11rKDSfzgXfvSIlDFUw"
upstream_id
"0217716156267282e03d1d5cb4d12864ab68947fc6ea2078e2fae"
total_cost
0.000516075
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Seed"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
491
0.01%
Dialogue to Total Word Ratio
Ratio: 63.75%, Deviation: 13.75%
neededClean
false
wordsTotal
491
wordsDialogue
313
46.8287%