NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FMZJ8TXSRJ2Q6EKYHEP6C
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.9s
Cost:
$0.000099
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.5180%
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 squinted at the inflatable bouncy castle across the yard. “Bill, I’m telling you, the haul is inside that rainbow-themed monstrosity.” Bill adjusted his ski mask, which smelled faintly of cheese. “We’re robbing a kid’s birthday party. We’re the worst people.” “We’re professional thieves, Bill. This is a legitimate target. Thirty gift bags, each with a two-dollar Slinky and a four-dollar action figure. That’s a hundred and eighty dollars in merchandise.” “Plus the piñata,” Bill mumbled. “I saw it. It’s a Unicorn. Probably stuffed with bubble gum.” “See? You’re in.” Molly pointed to the back door. “The parents are drinking sangria on the patio. We slip in, grab the presents from under the ‘Happy 7th Birthday, Timmy’ banner, and exit through the garage. Clean. Quiet.” “What about the kids?” “They’re in the bounce house. They can’t see us. They’re clouds of sugar and chaos.” Bill sighed. “Fine. But if I get hit by a glitter bomb, I’m billing you for therapy.” “Deal. Now move. And stop breathing on the fence—your breath leaves condensation.”
created_at
"2026-04-25T14:10:43.917Z"
4/25/2026, 2:10:43 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
797
moderation_latency
(null)
generation_time
4818
tokens_prompt
77
tokens_completion
344
native_tokens_prompt
67
native_tokens_completion
321
native_tokens_completion_images
(null)
native_tokens_reasoning
47
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
0.00009926
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"9adb4365-7992-45ef-a5be-00076043ed5d"
is_byok
false
latency
280
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-1777126243-Tcruugp8jOfejR9cTtPx"
session_id
(null)
api_type
"completions"
id
"gen-1777126243-b0GFhPWZSTW3CMCHKIMl"
upstream_id
"9adb4365-7992-45ef-a5be-00076043ed5d"
total_cost
0.00009926
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
174
0.00%
Dialogue to Total Word Ratio
Ratio: 83.05%, Deviation: 33.05%
neededClean
false
wordsTotal
177
wordsDialogue
147
0.5180%