NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2H10JVN2XV1PV987SZ3KRT
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.3s
Cost:
$0.000334
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
40.0831%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“So the clown is the key.” “The clown is always the key, Bill. We rent a suit, one of us gets funny, the other works the table.” “I’m not being the clown.” “You’re too tall to be a child, Bill. You’d look like a stork who’s failed three grades.” “Fine. I’ll be the clown. What’s the clown’s name?” “Bubbles.” “I’m not answering to Bubbles.” “You’ll answer to whatever a five-year-old screams while yanking your novelty bow tie. What’s the gig?” “I slide in, honk a horn, twist a poodle, keep eyes on me. You?” “I’m the estranged aunt with a tragic gift-wrapping addiction. I swoop in, pile the presents into a stroller, and vanish.” “Whose stroller?” “I’ll borrow one. Park it outside. Maybe put a doll in it for credibility.” “And the loot?” “All those shiny boxes stacked on the buffet table like a glittering, unprotected Fort Knox. Little Timmy’s getting an iPad. I read the tag. Little Timmy’s having a very bad birthday.” “What about the parents?” “They’ll be three Chardonnays deep and filming your tragic balloon animal collapse. We go in when the sugar rush peaks, and leave when the first child vomits.” “That’s our cue?” “That’s nature’s smoke bomb.” “I’ll need bigger shoes.” “I’ll need a bigger stroller. Let’s go practice your squeaky voice.”
created_at
"2026-04-25T14:34:46.751Z"
4/25/2026, 2:34:46 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
643
moderation_latency
(null)
generation_time
9213
tokens_prompt
77
tokens_completion
374
native_tokens_prompt
67
native_tokens_completion
350
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.000333645
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"511adcd2-c971-4dc8-8fd6-cdc489c9a06d"
is_byok
false
latency
284
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-1777127686-q3fZLE5zNZsGSU0xlajO"
session_id
(null)
api_type
"completions"
id
"gen-1777127686-WlvVyOdejtShSZm8A62Q"
upstream_id
"511adcd2-c971-4dc8-8fd6-cdc489c9a06d"
total_cost
0.000333645
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
217
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
220
wordsDialogue
220
40.0831%