Run: 2026-02-20-01KHYAD3BEAPZPPSGQTT09JEF5

Run Details

Duration:
1m 7s
Cost:
$0.006471
Provider:
Seed

Evaluation summary

Score Evaluator
Details Link
99.74% Matches word count (details)
39.70% Dialogue to Total Word Ratio (details)
69.7216% 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
Molly picks at a cherry lollipop pilfered from a corner store, gaze pinning the backyard party’s gift table—stacked with glitter-wrapped boxes flanked by a bobbing unicorn piñata. Bill shifts a crumpled blueprint in his lap, scuffing a scuffed white sneaker against the park bench’s splintered leg, his neon fanny pack slipping off one hip. A distant child’s shriek makes him flinch; he tucks the blueprint into his pack, glances at Molly’s chipped nail polish, adjusts his pack, squints at the bouncy castle where kids tumble quietly, completely unawares of their little impending silly gift heist. “You sure the cake’s fizzy distraction hits at 3 sharp?” Molly asks, popping her lollipop out to gesture quickly at the bustling venue. “Positive—my cousin’s the baker, slipped an extra carbonated layer to make it foam over and chaotic screams erupt,” Bill says, tapping his bulging pack. “What about the balloon-obsessed fluffy dog?” “I laced a peanut butter treat with mild sedative—he’ll nod off softly in 10 minutes,” he replies. “Lego set first or tiny gift bags?” “Lego’s top—my niece’s begged for it for months straight,” Molly says. “Escape tunnel’s under dandelions?” “Lawn gnome-hiding one—I dug it carefully last night,” Bill confirms.
created_at"2026-02-20T20:03:35.928Z" 2/20/2026, 8:03:35 PM
model"bytedance-seed/seed-1.6-20250625"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency564
moderation_latency(null)
generation_time66597
tokens_prompt77
tokens_completion2814
native_tokens_prompt147
native_tokens_completion3217
native_tokens_completion_images(null)
native_tokens_reasoning2911
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"
usage0.00647075
router(null)
provider_responses
0
endpoint_id"d85c3862-4e0d-4f8d-955b-babc62f98124"
id"02177161781607199b13dab45b2d10982c2cf34f4d4639d58e3d6"
is_byokfalse
latency564
model_permaslug"bytedance-seed/seed-1.6-20250625"
provider_name"Seed"
status200
api_type"completions"
id"gen-1771617815-6rROfLBDQeUljJbV61Ir"
upstream_id"02177161781607199b13dab45b2d10982c2cf34f4d4639d58e3d6"
total_cost0.00647075
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
99.74% Matches word count n/a
neededCleanfalse
words204
39.70% Dialogue to Total Word Ratio
Ratio: 40.20%, Deviation: 9.80%
neededCleanfalse
wordsTotal204
wordsDialogue82
69.7216%