NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DP41KEFX0WMDDK7SGH1ZZ
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.7s
Cost:
$0.000311
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
25.9628%
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
The problem, as Molly saw it, wasn’t the laser grid protecting the bouncy castle antechamber, but Bill’s complete inability to grasp the supply chain logistics of a five-year-old’s birthday. He was sweating through his clown makeup and staring at a pocket watch that was actually a Geiger counter, which was classic Bill. “The device is in the piñata,” Molly whispered, adjusting the oversized daisy on her lapel, which squirted a concentrated sedative. “You’re the mime. Mime an invisible box around the mountain of presents.” Bill mimed bumping into a wall, his expression professionally tragic. “Not a wall, a box. A container for the loot. We can’t just wheel a duffel bag past the face-painter, she’s ex-Mossad.” Molly’s daisy twitched, disabling a motion sensor shaped like a cartoon puppy. “You’ll scoop the haul and look artistically burdened. It’s a commentary on childhood materialism.” Bill silently mouthed a single, emphatic word, his white-gloved hands fluttering like trapped doves. “No, you can’t just use your invisible jetpack. The ceiling is festooned with parental paranoia. My intel says the birthday boy’s mother reviews the security footage frame by frame with a glass of pinot noir. We are not creating a viral moment. We are becoming a silent, tragic, present-stealing void. Now, are you ready to be a vessel of loss?”
created_at
"2026-04-25T13:36:24.118Z"
4/25/2026, 1:36:24 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
704
moderation_latency
(null)
generation_time
8642
tokens_prompt
77
tokens_completion
361
native_tokens_prompt
67
native_tokens_completion
324
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
0.000311025
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"407dd614-f726-4736-9480-15de2468a82f"
is_byok
false
latency
273
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-1777124184-KikdWlrHfaR7SpjCBt7f"
session_id
(null)
api_type
"completions"
id
"gen-1777124184-8XATldNePGL7eQnnEJ00"
upstream_id
"407dd614-f726-4736-9480-15de2468a82f"
total_cost
0.000311025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
216
0.00%
Dialogue to Total Word Ratio
Ratio: 52.49%, Deviation: 42.49%
neededClean
false
wordsTotal
221
wordsDialogue
116
25.9628%