Run: 2026-03-03-01KJTY2GS1YYB5SD5PXCAGXW3M

Run Details

Duration:
2m 54s
Cost:
$0.002849
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
98.71% Matches word count (details)
88.61% Dialogue to Total Word Ratio (details)
93.6595% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 bleached pink and blue backyard streamers into soft smudges as Molly and Bill crouched, squinting through the hedge’s thick leaves, behind an overgrown boxwood hedge. The distant thrum of a bounce house mixed with high, scratchy children’s yelps, laughter bouncing off the neighboring ranch siding. Bill hovered over the sliding glass patio lock, his lock pick slipping for the third time, sending a quiet clink against stone pavers. Molly prodded his thigh with her crumpled black mask, breath coming in sharp, irritated huffs. “Stop fidgeting so much, I’m almost through the lock,” Bill grumbled. “Hurry—they’re herding the kids to the cake table right now,” Molly hissed. They’d spent three weeks mapping the party’s layout, memorizing harried parents’ patrol routes, stashing empty gift bags in their backpacks’ false bottoms. The front hall was stacked with wrapped presents, bright with cartoon bows and glittery accents, the target they’d scouted for an unassuming heist. A plastic tiara flashed through the cracked patio screen, and Bill fumbled again, elbow knocking over a potted petunia. Molly clamped a hand over his mouth as a group of toddlers trundled past the hedge, clutching half-eaten lollipops and sticky balloon strings.
created_at"2026-03-03T22:46:04.849Z" 3/3/2026, 10:46:04 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1026
moderation_latency(null)
generation_time174182
tokens_prompt77
tokens_completion5680
native_tokens_prompt101
native_tokens_completion7097
native_tokens_completion_images(null)
native_tokens_reasoning6816
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"
usage0.0028489
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"021772577965648f6062c0432612ee8d02c106a4a44501041831a"
is_byokfalse
latency1026
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772577964-UkpUjphqFLeojDiXaYDh"
upstream_id"021772577965648f6062c0432612ee8d02c106a4a44501041831a"
total_cost0.0028489
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
98.71% Matches word count n/a
neededCleanfalse
words194
88.61% Dialogue to Total Word Ratio
Ratio: 15.90%, Deviation: 5.90%
neededCleanfalse
wordsTotal195
wordsDialogue31
93.6595%