NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2HE5H2RTKWAXZ5S859D06D
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
18.8s
Cost:
$0.000495
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
43.1902%
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 squinted at the crudely drawn map on the napkin, a smear of ketchup marking the bouncy castle. She adjusted her oversized party hat. “The loot’s piled by the piñata, shaped like a cartoon dinosaur that’s seen things. I’ve sourced elf costumes with reinforced candy pockets. You bring the clown nose.” Bill shuddered, his massive frame crammed into a tiny plastic chair. “Noses trap moisture, Moll. My nose gets damp, I panic, I confetti the joint prematurely. What about the distraction?” “I’m hiring an off-duty magician’s rabbit. Vicious thing, hates the birthday song.” Bill tapped his chin, leaving a sticky fingerprint. “The cake’ll be a diorama of despair. I can’t eat chocolate by volume; it mutes my ninja instincts. Can we do a smash-and-grab instead? I roar, you scoop.” “Absolutely not. This is a precision joy heist, Bill. We vanish into the chaos of pin-the-tail-on-the-donkey. You operate on a strict giggle-only basis.” Bill sighed, a wistful, hungry sound. “Giggling it is. But I’m palming a cupcake. The one with the tiny fire truck on top. It’s non-negotiable.” He stood up, his elf hat jingling defiantly with a hidden lockpick.
created_at
"2026-04-25T14:41:59.44Z"
4/25/2026, 2:41:59 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1832
moderation_latency
(null)
generation_time
17105
tokens_prompt
77
tokens_completion
565
native_tokens_prompt
67
native_tokens_completion
535
native_tokens_completion_images
(null)
native_tokens_reasoning
234
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
0.000494595
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"4504df30-c748-42e0-9158-be2f7158cb71"
is_byok
false
latency
555
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-1777128119-tMiBzNlRRZMjdr37psw1"
session_id
(null)
api_type
"completions"
id
"gen-1777128119-BeWxAqpOOD5qCOaVDCio"
upstream_id
"4504df30-c748-42e0-9158-be2f7158cb71"
total_cost
0.000494595
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
0.00%
Dialogue to Total Word Ratio
Ratio: 69.35%, Deviation: 19.35%
neededClean
false
wordsTotal
199
wordsDialogue
138
43.1902%