NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFBTR7THYY9XT3D0P3T3E5P
Run Details
Model:
ByteDance Seed 2.0 Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
30.6s
Cost:
$0.002571
Provider:
Seed
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.77%
Dialogue to Total Word Ratio
(details)
99.8760%
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 a thorny rose bush at the edge of a suburban cul-de-sac, Molly adjusted her too-tight cat burglar balaclava that kept slipping over her eyes, while Bill prodded a crumpled party route map he’d scribbled on a grease-stained Taco Bell napkin. Down the lawn, a seven-year-old’s birthday party blared the Encanto soundtrack, a lopsided T-Rex piñata swayed from an oak, and piles of wrapped presents teetered by the unlocked back patio, unguarded while the mom herded a pack of sugar-crazed kids inside for cake. “You sure this is foolproof? Last time we swiped a kid’s Lego Millennium Falcon you cried and gave it to a little league team,” Bill hissed, swatting a mosquito off his neck. “That was different! That kid had a pony, this one’s got three Switch games and a giant slime kit worth more than our last three gas station heists combined. I didn’t cry, the rose bush pricked me,” Molly snapped, whacking his arm. “Wait, what if we get caught? What do we even say? ‘Sorry ma’am, just robbing a first grader’?” Bill whispered. “We’re the piñata return guys. Now move, before the cake’s cut, and stop stepping on my $12 rental cape.”
created_at
"2026-03-11T21:11:19.047Z"
3/11/2026, 9:11:19 PM
model
"bytedance-seed/seed-2.0-lite-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
717
moderation_latency
(null)
generation_time
30554
tokens_prompt
77
tokens_completion
1250
native_tokens_prompt
115
native_tokens_completion
1271
native_tokens_completion_images
(null)
native_tokens_reasoning
977
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
0.00257075
router
(null)
provider_responses
0
endpoint_id
"bf1a3473-7a0a-46d3-aaa5-adb8f876a697"
id
"0217732634794749aa9d0b0344e85196ac345634277259c84464d"
is_byok
false
latency
717
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-1773263479-49H7ms1Hu8bWQsNMzRGs"
upstream_id
"0217732634794749aa9d0b0344e85196ac345634277259c84464d"
total_cost
0.00257075
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Seed"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
99.77%
Dialogue to Total Word Ratio
Ratio: 47.80%, Deviation: 2.20%
neededClean
false
wordsTotal
205
wordsDialogue
98
99.8760%