NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DFH0WNF1FDSWGYKY64TJ5
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.0s
Cost:
$0.000095
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
28.4888%
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
“Bill, I’m telling you, the bounce house is a decoy.” “Molly, the perimeter is a twelve-foot inflatable castle. That’s not a decoy, that’s a fortress of fun.” “Okay, but the real haul is in the piñata.” “The piñata? It’s filled with Tootsie Rolls and cheap plastic frogs.” “No, you numbskull. The body of the clown is the piñata.” “We’re stealing a clown?” “Not the clown, the clown’s pants. The birthday kid’s dad is a jeweler. He hides diamond studs in the elastic waistband.” “So we’re robbing a clown’s trousers at a five-year-old’s party for horse hoofs?” “Diamonds, Bill. And the code for the safe is ‘Blippi12.’ I heard the mom whisper it to the caterer.” “Why do you know all this?” “I’m wearing the inflatable T-Rex costume. Kids tell me everything.” “You’re the T-Rex? I was going to trip that guy.” “You’d have tripped the dad. He’s the T-Rex. I’m the one giving balloon animals. Want a weiner dog?” “I want a new partner.” “Too late. Here comes the goody bags. Move, or I’m leaving you for the pony ride.”
created_at
"2026-04-25T13:32:48.151Z"
4/25/2026, 1:32:48 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
539
moderation_latency
(null)
generation_time
4577
tokens_prompt
77
tokens_completion
317
native_tokens_prompt
67
native_tokens_completion
305
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
0.00009478
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"097248f9-032c-4fcb-be3d-829697e923e4"
is_byok
false
latency
279
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-1777123968-lEbCmVRhbM46NKFR3Ort"
session_id
(null)
api_type
"completions"
id
"gen-1777123968-TC3wCZsN2bPA1sYkjfix"
upstream_id
"097248f9-032c-4fcb-be3d-829697e923e4"
total_cost
0.00009478
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
183
wordsDialogue
183
28.4888%