NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9JSEPAT23C59VJPH4KJJ9
Run Details
Model:
ByteDance Seed 1.6
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
46.3s
Cost:
$0.003503
Provider:
Seed
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 vinyl booth at Joe’s Diner stuck to Molly’s thigh, a grease stain blooming on her black hoodie where she’d leaned against a ketchup-smeared tray. She stirred her decaf coffee with a plastic dinosaur spoon, a dollar-store toy tiara twirling between her free fingers—practice for the kids’ party’s princess theme. Bill hunched across from her, scribbling a lopsided floor plan on a napkin with a broken crayon, a half-eaten cherry pie oozing filling onto his notebook. The diner’s jukebox blared a tinny “Happy Birthday,” making him flinch. The present table’s tucked by the ball pit—prime real estate, no adult supervision after cake cutting. Cake cutting’s at 3, but the party clown does a balloon animal demo at 2:45. You gonna dodge a polka-dot-suited guy wielding a helium tank? I’ve dodged security dogs twice my size; a clown’s child’s play. You cried at the circus when you were 12 because a clown handed you a squirt-flower. That was a tactical retreat—he had a squirt gun in his cufflinks. Unethical. What about the balloon arch? You scribbled “death trap” on the napkin, but you didn’t outline a workaround. Bubble solution. I’ll squirt the arches, they’ll stick together—easy to step over. Bubble solution? That’s a party favor, not a heist tool. I was a party clown for six months—bubble solution solves 90% of crises. The other 10% involves cake frosting and regret. The birthday boy’s 7-year-old cousin’s a walkie-talkie-wielding secret agent. He guards the present table like it’s a diamond vault. I’ll distract him with a rubber chicken trick—pull it from my pocket, he’ll forget his post. A rubber chicken? That’s ridiculous. He’s 7. Ridiculous is his love language. You gonna carry the presents in a backpack? The wrapping paper’ll crinkle—alert every adult within 10 feet. I’ve got a cloth sack lined with felt—no crinkles, fits 12 presents max. We’ll make two trips. Two trips? That doubles our risk of getting caught by the mom who’s refilling the juice boxes. That mom’s drunk on mimosa punch. She’ll be napping on the couch by 2:30. Molly snickered, dropping the dinosaur spoon into her coffee with a clink. She plucked the napkin from Bill’s hand to circle the balloon arch, the waitress sliding a refilled pie slice in front of him without a word. Bill crumpled the napkin into the pie tin, placing the toy tiara on his head with a scowl. Molly snapped a photo with her phone to blackmail him later. The jukebox switched to a country song, and they checked their watches—2 hours until the party, 1 helium tank to dodge, and a mountain of wrapped presents waiting for their less-than-heroic heist.
created_at
"2026-02-20T19:49:13.825Z"
2/20/2026, 7:49:13 PM
model
"bytedance-seed/seed-1.6-20250625"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1120
moderation_latency
(null)
generation_time
46128
tokens_prompt
77
tokens_completion
1816
native_tokens_prompt
147
native_tokens_completion
1733
native_tokens_completion_images
(null)
native_tokens_reasoning
1060
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
0.00350275
router
(null)
provider_responses
0
endpoint_id
"d85c3862-4e0d-4f8d-955b-babc62f98124"
id
"021771616954417e1f2c28e220bf76d8a56e2a46eaa08e9d8fa5b"
is_byok
false
latency
1120
model_permaslug
"bytedance-seed/seed-1.6-20250625"
provider_name
"Seed"
status
200
api_type
"completions"
id
"gen-1771616953-T8TdvNGz03qO3vcWATIU"
upstream_id
"021771616954417e1f2c28e220bf76d8a56e2a46eaa08e9d8fa5b"
total_cost
0.00350275
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Seed"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
461
0.00%
Dialogue to Total Word Ratio
Ratio: 1.74%, Deviation: 48.26%
neededClean
false
wordsTotal
461
wordsDialogue
8
0.0000%