Run: 2026-02-20-01KHY9GBTEKWCFQ4GN79T9TVWC

Run Details

Duration:
9.3s
Cost:
$0.000331
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
43.38% Matches word count (details)
99.20% Dialogue to Total Word Ratio (details)
71.2883% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 200 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 sun dipped low, gilding the backyard where a bouncy castle squelched under a toddler’s jump and a teddy bear piñata hung crookedly from an oak. Molly adjusted her flour-dusted glasses, eyeing the presents by the sliding door—stuffed animals, a tablet, a bike, maybe. “Stuffed animals are cute, but the bike *could* be useful,” she said, poking a teddy. Bill, already scaling the fence, turned. “Useful? We’ll sell it by noon. Priorities, Moll. The piñata’s full of candy—*good* candy, not that chalky party bag stuff.” Molly sighed. “What if the mom—?” Bill dropped down, grinning. “Mom’s gabbing with the dentist. Her back’s to us. Piñata first, presents later. Quick as a sneeze.” He nodded at the piñata, which creaked. Molly glanced at a little boy in a cape, picking lollipops. “And what if he—?” “He’ll be too busy with his lollipop to notice. Now move—before the pizza arrives. *Pizza* is the real danger. Can’t have tomato sauce on my getup.” Molly grabbed a duffel. “If we get caught, I’m blaming you.” Bill winked. “Deal. I’ll tell ’em you were a *volunteer*. Kids love volunteers. Maybe they’ll give us extra juice boxes.” He tugged her toward the door. “C’mon, thief. Let’s make a toddler very sad.” They slipped inside, the piñata creaking like a conspirator.
created_at"2026-02-20T19:47:54.329Z" 2/20/2026, 7:47:54 PM
model"bytedance-seed/seed-1.6-flash-20250625"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency672
moderation_latency(null)
generation_time9173
tokens_prompt77
tokens_completion1068
native_tokens_prompt149
native_tokens_completion1066
native_tokens_completion_images(null)
native_tokens_reasoning714
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"
usage0.000330975
router(null)
provider_responses
0
endpoint_id"e01a1227-001b-44d4-a376-90850668fa84"
id"021771616874672c95e3350f28d4e5f7ad155450ef541a31c9fbe"
is_byokfalse
latency498
model_permaslug"bytedance-seed/seed-1.6-flash-20250625"
provider_name"Seed"
status200
api_type"completions"
id"gen-1771616874-jphAAK2Lci67IZXIuGfz"
upstream_id"021771616874672c95e3350f28d4e5f7ad155450ef541a31c9fbe"
total_cost0.000330975
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
43.38% Matches word count n/a
neededCleanfalse
words217
99.20% Dialogue to Total Word Ratio
Ratio: 53.00%, Deviation: 3.00%
neededCleanfalse
wordsTotal217
wordsDialogue115
71.2883%