NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2J08YNQKXKTE0T57N97K0C
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.8s
Cost:
$0.000097
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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 flattened the creased blueprint against the greasy diner table. “Okay, target’s the Bouncy Castle of Eternal Sorrow. No, wait, that’s the one next door.” Bill stabbed a greasy french fry into a ketchup puddle. “Themed party. ‘Princess Sparklehorn’s Realm of Glitter.’ I’m allergic to glitter.” “You’re allergic to joy,” Molly said. “We go in as the ‘Gift Voucher and Removal Specialists.’ You wear the rainbow unicorn head, I handle the loot.” “Loot? It’s a seven-year-old’s stash. We’re getting foam swords and a remote control that only works for the first five feet.” “And a signed photo of the local weatherman,” Molly added. “He’s a regional treasure.” Bill groaned. “Why not just swipe the birthday cake? It’s chocolate. No glitter.” “Because the cake is a decoy,” Molly said, tapping the blueprint. “The real haul is in the Goody Bag Fortress, behind the pinata. We need a diversion. Something adults will ignore completely.” “Like a child crying about a lost balloon?” “No, that gets attention. We need a grown-up crying about a lost 401k. I’ll fake a phone call with my accountant. You sneak in.” Bill stared at her. “You have an accountant?” “No, but I have a very convincing voice for financial despair.”
created_at
"2026-04-25T14:51:51.13Z"
4/25/2026, 2:51:51 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
823
moderation_latency
(null)
generation_time
5690
tokens_prompt
77
tokens_completion
355
native_tokens_prompt
67
native_tokens_completion
314
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
0.0000973
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"1bfd543f-5523-4d79-b068-b98aef749701"
is_byok
false
latency
310
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-1777128711-njiwaulBA9zAt1Rc93V1"
session_id
(null)
api_type
"completions"
id
"gen-1777128711-cOUZ65AJVX7CL1ZZ71hp"
upstream_id
"1bfd543f-5523-4d79-b068-b98aef749701"
total_cost
0.0000973
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
0.00%
Dialogue to Total Word Ratio
Ratio: 83.01%, Deviation: 33.01%
neededClean
false
wordsTotal
206
wordsDialogue
171
49.9595%