NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2EV8N0HHMEF6E7S4WNSTRX
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.5s
Cost:
$0.000102
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
82.39%
Dialogue to Total Word Ratio
(details)
89.1862%
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
“You sure about this, Molly?” Bill whispered, huddled behind a bouncy castle. “Of course I’m sure. The birthday girl’s name is Lily. She’s seven. She’ll have thirty loot bags, each stuffed with candy and plastic junk we can sell on eBay.” “eBay? We’re stealing from a child and flipping it on eBay?” “Don’t get moral on me. You ate three of her cupcakes in the bush.” “They were vanilla. Irresistible. But what’s the plan? We can’t just walk in.” “We’re party clowns. I’m Trixie the Tickler. You’re Bongo the Bonker.” “Bongo the Bonker? That sounds like a bad magician with a criminal record.” “Focus. I’ll do balloon animals while you set up the ‘magic trunk.’ We swap the real presents for empty boxes during the ‘Great Disappearing Gift Trick.’” “And if a kid wants their present back?” “Then Bongo gives them a very sad face and a lollipop. They’re seven. They’ll forget by snack time.” “And the parents?” “The parents will be drunk on fruit punch. Look, the banner says ‘Presents under the rainbow arch.’ I’ll distract. You grab. Three minutes, in and out.” “Three minutes. Fine. But if I get glitter on my new gloves, I’m billing you for dry cleaning.” “Deal. Now smile. It’s showtime, Bongo.”
created_at
"2026-04-25T13:56:41.252Z"
4/25/2026, 1:56:41 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
513
moderation_latency
(null)
generation_time
5391
tokens_prompt
77
tokens_completion
361
native_tokens_prompt
67
native_tokens_completion
330
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
0.00010178
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"2a275b9f-44bf-4c92-acf4-7849e024a1f3"
is_byok
false
latency
288
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-1777125401-x868vsL1LiuN98m4doHp"
session_id
(null)
api_type
"completions"
id
"gen-1777125401-slo05r3mOjaZ3TnnzMpw"
upstream_id
"2a275b9f-44bf-4c92-acf4-7849e024a1f3"
total_cost
0.00010178
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
82.39%
Dialogue to Total Word Ratio
Ratio: 96.63%, Deviation: 6.63%
neededClean
false
wordsTotal
208
wordsDialogue
201
89.1862%