NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2GVXMVNVJAR7WX391A27VS
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.7s
Cost:
$0.000106
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
21.6892%
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
Molly squinted through the binoculars at the bouncy castle. “That’s the gift table. Ten feet from the cake, guarded by a woman with a glittery eye patch and a toddler who bites.” Bill, chewing a party blower, mumbled, “The kid bit me last week for a jelly bean.” “He’s their security detail.” “I got a plan,” Bill said, spitting out the blower. “We go in as clowns. They love clowns.” “You look like a sad raspberry,” Molly said. “And you squeak when you walk.” “It’s a prosthetic squeak. Adds authenticity.” “Fine,” she said, lowering the binoculars. “But if we get cornered, you’re the balloon animal sacrifice.” Bill grinned, adjusting a rainbow wig over his bald spot. “Worth it for that remote-control dinosaur.” “It’s a tricycle, Bill.” “With lasers. The invitation said ‘space adventurers.’” He held up a crinkled card. “We’re bringing the asteroid.” Molly sighed. “You’re the reason we’re banned from three Chuck E. Cheeses.” “Four now. I’m building a legacy.” Above them, a piñata burst, showering candy onto the lawn. Bill’s eyes went wide. “The haul’s gonna be epic.” “Or we’ll end up in a ball pit full of glitter and regret.” “Regret’s a payment plan for joy,” Bill said, and offered her a red nose. “You in?” Molly took it. “You owe me a pizza.”
created_at
"2026-04-25T14:31:59.903Z"
4/25/2026, 2:31:59 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
909
moderation_latency
(null)
generation_time
5611
tokens_prompt
77
tokens_completion
385
native_tokens_prompt
67
native_tokens_completion
345
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
0.00010598
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"16e834bb-c5b4-40ce-9410-b5e58c2b25f3"
is_byok
false
latency
471
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-1777127519-an97paKD7OcKru0DPeLK"
session_id
(null)
api_type
"completions"
id
"gen-1777127519-eMgXGMgy7b3gkvc0C6ku"
upstream_id
"16e834bb-c5b4-40ce-9410-b5e58c2b25f3"
total_cost
0.00010598
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
0.00%
Dialogue to Total Word Ratio
Ratio: 67.43%, Deviation: 57.43%
neededClean
false
wordsTotal
218
wordsDialogue
147
21.6892%