Run: 2026-02-20-01KHY883W6VHKBB8YJNTDS4P1Y

Run Details

Duration:
39.7s
Cost:
$0.003171
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
75.16% Matches word count (details)
99.49% Dialogue to Total Word Ratio (details)
87.3220% Overall

Model input

User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
Molly leans against a chipped park bench, crumpling a neon children’s party invite in one fist while Bill jiggles a lopsided fake balloon dog in the other. “Confirm the party’s 3pm start?” “Yep—cake cut at 4, that’s our chaos window.” “Cake swarms mean parents’ eyes glued to icing messes, not the gift table.” “Gift table’s behind the piñata, right? Tinsel-draped?” “Exactly—hard to miss but easy to grab in costumes.” “I brought a neon clown wig—you take the fairy wings I snagged?” “Fairy’s better—kids let fairies hover near presents without squawking.” “What about the dinosaur-suited bouncer?” “I’ll slip him a lollipop spiked with sleep syrup—nods off in five.” “Stolen lollipop?” “Corner store yesterday—perfectly dosed.” “Kid witness plan?” “Tell ’em we’re gift fairies rearranging for Santa’s check.” “Santa angle’s genius—they’ll zip it.” “Stash loot in a giant beach bag under the slide.” “Slide stash—smart.” “Meet at the oak tree post-heist, split by loot value.” “What about the sticky candy-filled presents?” “I take those—you hate sticky.” “Deal.” “Don’t forget your wig—last time you forgot disguise and got chased by a goose.” “I won’t—goose trauma’s still fresh.” “Good—one misstep and we’re stuck explaining to tantrum-throwing six-year-olds why we’re stealing their toy trucks.”
created_at"2026-02-20T19:25:55.473Z" 2/20/2026, 7:25:55 PM
model"bytedance-seed/seed-1.6-20250625"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1749
moderation_latency(null)
generation_time39570
tokens_prompt77
tokens_completion1652
native_tokens_prompt147
native_tokens_completion1567
native_tokens_completion_images(null)
native_tokens_reasoning1223
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"
usage0.00317075
router(null)
provider_responses
0
endpoint_id"d85c3862-4e0d-4f8d-955b-babc62f98124"
id"021771615556001a491eea4a025beb52fc51c9506f8c2b2a7aa9f"
is_byokfalse
latency1749
model_permaslug"bytedance-seed/seed-1.6-20250625"
provider_name"Seed"
status200
api_type"completions"
id"gen-1771615555-98bgEkpdHehPnPQm8ZEQ"
upstream_id"021771615556001a491eea4a025beb52fc51c9506f8c2b2a7aa9f"
total_cost0.00317075
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
75.16% Matches word count n/a
neededCleanfalse
words213
99.49% Dialogue to Total Word Ratio
Ratio: 87.32%, Deviation: 2.68%
neededCleanfalse
wordsTotal213
wordsDialogue186
87.3220%