NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DQN0ZRAD7KNRRVVT1X1KJ
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.4s
Cost:
$0.000101
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
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 adjusted the strap of her black duffel bag, peering through the hedge. “Okay, so the bounce house is a distraction. I’ll cause a sugar-high stampede at the cupcake table.” Bill, wedged behind a rhododendron, squinted. “And I’m supposed to what, impersonate the magician? I don’t know any tricks.” “You know the ‘pull a coin from an ear’ bit,” Molly said, not looking at him. “Kids love that.” “I pull a nickel from a kid’s ear, they expect the rest of the bank,” Bill grumbled. “And where are you while I’m doing that?” “Grabbing the gift pile. It’s a rainbow of unopened loot.” She smiled. “A clown car’s worth of gratitude.” “What if the birthday girl cries? She’s five, Molly. Five.” “Then you do the disappearing act. I’ll grab the bags, we meet at the fence, and we’re gone before the piñata’s breached.” Bill shook his head. “We’re ruining a child’s good time for a bundle of art supplies and a talking dinosaur.” “Don’t forget the gift cards,” Molly said, zipping her bag. “That’s why we’re here, Bill. It’s not personal. It’s business.” “Business,” he repeated, watching a toddler wobble past with a balloon. “You know, I kind of liked you better when you stole cars.”
created_at
"2026-04-25T13:37:14.277Z"
4/25/2026, 1:37:14 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
960
moderation_latency
(null)
generation_time
5121
tokens_prompt
77
tokens_completion
350
native_tokens_prompt
67
native_tokens_completion
326
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
0.00010066
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"48d8ff1e-bcfd-4240-99de-07679f3d2994"
is_byok
false
latency
515
model_permaslug
"deepseek/deepseek-v4-flash-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-1777124234-R5NNmX1gQ5SI6kfuRvlW"
session_id
(null)
api_type
"completions"
id
"gen-1777124234-AQyPNvvBVcIqFyBxCbuq"
upstream_id
"48d8ff1e-bcfd-4240-99de-07679f3d2994"
total_cost
0.00010066
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
0.00%
Dialogue to Total Word Ratio
Ratio: 76.81%, Deviation: 26.81%
neededClean
false
wordsTotal
207
wordsDialogue
159
49.3562%