NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFGH366KJ4YAGZ6PZ2VE7VV
Run Details
Model:
ByteDance Seed 2.0 Lite
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
44.3s
Cost:
$0.003621
Provider:
Seed
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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
Molly and Bill huddled behind an overgrown hydrangea bush across from the suburban ranch, their lumpy black ski masks askew, Molly clutching a fanny pack of stolen party blowers, Bill gripping a frayed garage-sale net he’d insisted was “top-tier heist equipment.” A gaggle of seven-year-olds chased a slobbering golden retriever across the lawn, a unicorn piñata swaying from the porch eaves, stacks of glitter-wrapped presents piling high by the unlocked back door. A tiny princess-costumed toddler had just started squinting hard in their direction. “You said the parents would be passed out on spiked punch!” Bill hissed, jabbing a gloved finger at a mom sprinting after a kid who’d climbed an oak tree, juice box sloshing in her wake. “That lady’s faster than the Apple Store security guard we outran last month!” Molly elbowed him hard, hissing back that she’d forgotten to spike the punch before they arrived, that they still had the element of surprise—until the toddler shrieked and pointed straight at their bush. Bill groaned, yanking his mask down. “We’re the worst thieves ever. I told you we should rob a library, no toddlers hoarding limited-edition LOL dolls ready to blow our whole operation.”
created_at
"2026-03-11T22:33:25.457Z"
3/11/2026, 10:33:25 PM
model
"bytedance-seed/seed-2.0-lite-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
765
moderation_latency
(null)
generation_time
44191
tokens_prompt
77
tokens_completion
1934
native_tokens_prompt
115
native_tokens_completion
1796
native_tokens_completion_images
(null)
native_tokens_reasoning
1523
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
0.00362075
router
(null)
provider_responses
0
endpoint_id
"bf1a3473-7a0a-46d3-aaa5-adb8f876a697"
id
"02177326840595007b4b942199433a510c68da6d01b36ec71eee0"
is_byok
false
latency
765
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-1773268405-Pdur6r166puv7sDSEay0"
upstream_id
"02177326840595007b4b942199433a510c68da6d01b36ec71eee0"
total_cost
0.00362075
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
0.00%
Dialogue to Total Word Ratio
Ratio: 26.11%, Deviation: 23.89%
neededClean
false
wordsTotal
203
wordsDialogue
53
49.9595%