NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2GE4MZ1Y06SNXF727PJMRC
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
14.1s
Cost:
$0.000360
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 peered through the grimy window of the community centre, her breath fogging the glass. Inside, a bouncy castle deflated listlessly like a sad, rubber dinosaur. “Right,” Bill whispered, unfolding a crinkled napkin with a crayon diagram. “Operation Kinder-Surprise. Phase one: infiltration.” “Through the ball pit,” Molly stated firmly. “It’s the only silent approach.” “It’s a logistical nightmare, Moll. That pit absorbs adult dignity faster than quicksand. We’ll go in via the fire exit, disguised as a late-arriving clown and his emotional-support mime.” Molly scoffed. “I’ve told you, I don’t mime. It’s a point of principle. My tragic backstory would just look like I’m stuck in a box I can’t afford.” “Fine. New plan. I’ll be a magician. You’re my dazzling assistant. We’ll saw the gift table in half.” “The whole table?” “Faster than unwrapping. We slap a sequinned cloth over the pile, a bit of sparkly misdirection, and when I say ‘Abracadabra,’ you shove the lot into a bin bag hidden behind my cape.” “And the thirty hyped-up kids on a sugar crash?” Molly asked, arching an eyebrow. “What’s the misdirection for them?” Bill grinned, producing a sleek remote control from his pocket. “The ultimate distraction. I call it the Great Sugar Liberation.” “You’re going to spike the juice with espresso, aren’t you?” “I prefer the term ‘anti-nap catalyst.’ While the tiny time-bombs are literally vibrating, we glide through chaos like elegant swans. Glittery, thieving swans.”
created_at
"2026-04-25T14:24:32.61Z"
4/25/2026, 2:24:32 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1008
moderation_latency
(null)
generation_time
9727
tokens_prompt
77
tokens_completion
426
native_tokens_prompt
67
native_tokens_completion
380
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
0.000359745
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"70c95969-7f62-4e4a-984c-29415613298f"
is_byok
false
latency
287
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-1777127072-gdT2BW8hGEx8rn1OHDGs"
session_id
(null)
api_type
"completions"
id
"gen-1777127072-U9yaN7MPWjaxFkmiGOND"
upstream_id
"70c95969-7f62-4e4a-984c-29415613298f"
total_cost
0.000359745
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
237
0.00%
Dialogue to Total Word Ratio
Ratio: 76.86%, Deviation: 26.86%
neededClean
false
wordsTotal
242
wordsDialogue
186
0.0000%