NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DJT080NCS78J8TYAVN6VW
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.0s
Cost:
$0.000469
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.21%
Matches word count
(details)
75.96%
Dialogue to Total Word Ratio
(details)
38.0868%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 squinted at the crudely drawn map on the napkin, its “X” marking the bounce house where the presents would be piled. Bill, meanwhile, was wrestling his head through the neck hole of a rented unicorn costume, the horn lolling sadly. The plan was elegant in its stupidity. He’d be the “surprise entertainment,” reduced to jingling a tambourine to mask the sound of her crawling through a gift-wrap tunnel. She tapped the napkin. “So you’re the unicorn, I’m the silent gift-worm.” He nodded, his face flushed inside the fur. “Exactly. Festive and invisible.” The horn flopped over his eyes, and he blew at it unsuccessfully, a puff of air ruffling the napkin. She pictured him trying to shimmy presents out of the pile under his costume while she slithered through a cardboard chute designed for toddlers. “What if a kid hugs you?” she asked. He paused, considering. “Disguise the loot as a piñata and run,” he wheezed, the costume’s fan having died. The sheer absurdity hung between them, a perfect, doomed masterpiece.
created_at
"2026-04-25T13:34:35.534Z"
4/25/2026, 1:34:35 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
814
moderation_latency
(null)
generation_time
11931
tokens_prompt
77
tokens_completion
552
native_tokens_prompt
67
native_tokens_completion
506
native_tokens_completion_images
(null)
native_tokens_reasoning
253
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.000469365
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"b38f9240-a65b-48d1-b090-41df217cd943"
is_byok
false
latency
278
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777124075-lvUklPW3oEobQH8FJTAp"
session_id
(null)
api_type
"completions"
id
"gen-1777124075-COCjiF5IIprCtuZ22hHb"
upstream_id
"b38f9240-a65b-48d1-b090-41df217cd943"
total_cost
0.000469365
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.21%
Matches word count
n/a
neededClean
false
words
172
75.96%
Dialogue to Total Word Ratio
Ratio: 17.24%, Deviation: 7.24%
neededClean
false
wordsTotal
174
wordsDialogue
30
38.0868%