NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2F795Q0NRNN23FYN86GF1A
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.9s
Cost:
$0.000098
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.91%
Dialogue to Total Word Ratio
(details)
97.9479%
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
“Okay, run it by me one more time,” Bill said, wiping his brow with a sleeve that smelled of old cheese and desperation. Molly sighed, tapping a diagram of the birthday girl’s backyard. “We go in as the cousin from out of town and the balloon delivery guy who got lost.” “I’m the lost balloon guy?” “You’re holding a balloon, Bill. A big one. Helium makes you less noticeable.” “My knees pop when I walk. They’ll hear me coming.” “They’re six years old, not bomb-sniffing dogs. Focus. The presents are in the gazebo. I distract Aunt Brenda by crying about my cat. You sweep the loot into the party-favor bags.” “What if the cat story gets me choked up? I’m sensitive.” “You don’t have a cat.” “I could borrow one. Make the lie airtight.” “No. You take the presents. I take the cake.” “The cake? That’s the mission? Sugar?” “That’s a two-hundred-dollar fondant atrocity shaped like a unicorn. We’re pawn shops, Bill, not saints. And when the chaos hits—the sugar crash, the tears, the piñata—we slip out the side gate.” “Which side gate?” “The one without the hysterical mother. You remembered the fake smile, right?” “I’m using it right now.” “That’s a panic-stricken grimace. Try again.”
created_at
"2026-04-25T14:03:15.003Z"
4/25/2026, 2:03:15 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
631
moderation_latency
(null)
generation_time
4841
tokens_prompt
77
tokens_completion
359
native_tokens_prompt
67
native_tokens_completion
317
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
0.00009814
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"8d4d0dfb-2bad-4a87-b007-8fc452ad0a5f"
is_byok
false
latency
273
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-1777125795-3M4tRyB7MReEtB8SyAk9"
session_id
(null)
api_type
"completions"
id
"gen-1777125795-DPcmeWgnWTlTNfvDj0vM"
upstream_id
"8d4d0dfb-2bad-4a87-b007-8fc452ad0a5f"
total_cost
0.00009814
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
99.91%
Dialogue to Total Word Ratio
Ratio: 88.26%, Deviation: 1.74%
neededClean
false
wordsTotal
213
wordsDialogue
188
97.9479%