NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFDXXCB4HYGA3CTMBMAYT78
Run Details
Model:
ByteDance Seed 2.0 Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
46.6s
Cost:
$0.003843
Provider:
Seed
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.06%
Dialogue to Total Word Ratio
(details)
49.9892%
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
Messages
Meta
AI
Crouched behind an overgrown holly bush at the edge of a suburban cul-de-sac, Molly adjusted her slipping black ski mask and prodded Bill in the ribs with a cheap gas-station plastic taser. Across the street, a seven-year-old’s birthday party blared cartoon theme songs, a squishy axolotl piñata swaying from the old oak, stacks of shiny wrapped presents teetering on a wobbly back-deck folding table. Bill’s fanny pack bulged with stolen party streamers and a half-eaten cherry popsicle he’d swiped from a passing kid; he’d already tripped over a concrete garden gnome twice, his crumpled clown face-paint costume digging into his ankles. “Remind me again why we bailed on the downtown bank heist to steal a bunch of random kids’ toys?” Bill whispered, yanking his mask up to scratch an angry mosquito bite on his jaw. “Last I checked, we’re professional thieves, not deadbeat party crashers.” “Because the bank has laser alarms and armed guards,” Molly hissed, shoving him lower when a frazzled mom chased a naked toddler past their hiding spot. “This party’s only security is a grandpa who passes out mid-piñata beatdown. And that Lego Millennium Falcon on top of the pile? Sold out everywhere. Grab the face paint. We’re going in.”
created_at
"2026-03-11T21:47:59.768Z"
3/11/2026, 9:47:59 PM
model
"bytedance-seed/seed-2.0-lite-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
908
moderation_latency
(null)
generation_time
46541
tokens_prompt
77
tokens_completion
1968
native_tokens_prompt
115
native_tokens_completion
1907
native_tokens_completion_images
(null)
native_tokens_reasoning
1614
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
0.00384275
router
(null)
provider_responses
0
endpoint_id
"bf1a3473-7a0a-46d3-aaa5-adb8f876a697"
id
"02177326568041334865fa4f4ec67e4268045741fa8093fdfae77"
is_byok
false
latency
908
model_permaslug
"bytedance-seed/seed-2.0-lite-20260309"
provider_name
"Seed"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773265679-4Kiuo8aHtDMwMMGQkuPO"
upstream_id
"02177326568041334865fa4f4ec67e4268045741fa8093fdfae77"
total_cost
0.00384275
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
203
0.06%
Dialogue to Total Word Ratio
Ratio: 33.49%, Deviation: 16.51%
neededClean
false
wordsTotal
212
wordsDialogue
71
49.9892%