NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9Z438CHY56YYMYHB50A4B
Run Details
Model:
ByteDance Seed 1.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.5s
Cost:
$0.000308
Provider:
Seed
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
25.50%
Dialogue to Total Word Ratio
(details)
62.7077%
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
Messages
Meta
AI
Alley light flickers. Bill squints at a crumpled map, soda sloshing. “Molly, those are *napkins* marked ‘security.’” He pokes it. “Toddler with a GoPro?” “Kid’s party,” she says, scrolling a list. “Piñata full of candy, but the loot’s in the red tent—Lego, a unicorn stuffie, *gold* sippy cup.” Bill snorts. “Unicorn stuffie? What, we gonna frame it? ‘Sorry, FBI, it’s a *vintage* heist artifact.’” She shoves him. “Ninja Turtle balloons mean no alarms—kids yank ’em down. But *duck tape* on the tent? Dammit, why’s the mom a former Brownie?” “She thinks it’s ‘decor.’” He rubs his stomach. “I’m not eatin’ cake with sprinkles. Last heist, that gluten-free flour gave me *IBS*.” “We’ll hit the piñata after—sugar high makes ’em hyper. You hide the sippy cup in your toolbox? The one with the inflatable flamingo?” He freezes. “You saw that? I lost that in ’08!” “Honey, I see *everything*.” She grins. “Now c’mon—if we’re late, the Goodie Bags’ll be gone. And *I* want a lollipop.” Bill sighs, tucking the map. “If I get covered in ketchup, I’m blaming you.” “Deal.” Light dims. Footsteps clatter. “Wait—where’s the *cake* map?” “Oh, that’s the *party invitation*. Dummy.”
created_at
"2026-02-20T19:55:57.938Z"
2/20/2026, 7:55:57 PM
model
"bytedance-seed/seed-1.6-flash-20250625"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
622
moderation_latency
(null)
generation_time
5296
tokens_prompt
77
tokens_completion
933
native_tokens_prompt
149
native_tokens_completion
991
native_tokens_completion_images
(null)
native_tokens_reasoning
619
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
0.000308475
router
(null)
provider_responses
0
endpoint_id
"e01a1227-001b-44d4-a376-90850668fa84"
id
"021771617358263f2dfc9d17a425ad03ee233374d263661528b9c"
is_byok
false
latency
514
model_permaslug
"bytedance-seed/seed-1.6-flash-20250625"
provider_name
"Seed"
status
200
api_type
"completions"
id
"gen-1771617357-gtizcRfF5CNAoJ3aiZml"
upstream_id
"021771617358263f2dfc9d17a425ad03ee233374d263661528b9c"
total_cost
0.000308475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Seed"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
25.50%
Dialogue to Total Word Ratio
Ratio: 79.19%, Deviation: 10.81%
neededClean
false
wordsTotal
197
wordsDialogue
156
62.7077%