NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FTCDCC3GQ9QXVEYYN7MWC
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.1s
Cost:
$0.000395
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
55.9718%
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
"We're not just waltzing in dressed as clowns, Bill. That's page one of the burglar's book of bad ideas." "Clowns are terrifying, Molly. Parents will be so busy shielding their kids they won't notice the presents walking out. It's psychological warfare." "Or they'll just form an angry parent circle and beat us with a piƱata stick. We need a subtler angle. What about the entertainment?" "Like a magician? I can pull a rabbit out of a hat." "You can pull a muscle reaching for a biscuit. I'm thinking more... petting zoo. We rent a couple of foul-tempered goats, create a diversion, I slip in as the harassed handler." "And I'm what, the goat whisperer?" "You're the one who 'accidentally' lets the birthday cake slide off the table and into the bouncy castle. Absolute chaos. In the frosting-smeared pandemonium, I load the gift table into our van disguised as a 'mobile petting zoo sanitation unit'." "Molly, that's genius. But won't the kids chase the goats?" "Exactly. They're our fuzzy, four-legged getaway drivers. We just follow the screaming and the trail of half-eaten party hats. It's the perfect crime."
created_at
"2026-04-25T14:13:40.912Z"
4/25/2026, 2:13:40 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
709
moderation_latency
(null)
generation_time
9996
tokens_prompt
77
tokens_completion
471
native_tokens_prompt
67
native_tokens_completion
421
native_tokens_completion_images
(null)
native_tokens_reasoning
151
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
0.000395415
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"a50bd234-ef7d-45b6-aa0c-b7fb880733eb"
is_byok
false
latency
282
model_permaslug
"deepseek/deepseek-v4-pro-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-1777126420-Uo6FuVdH68pmBoc9hpiC"
session_id
(null)
api_type
"completions"
id
"gen-1777126420-9c7vwuhn3vlBukwh7ua4"
upstream_id
"a50bd234-ef7d-45b6-aa0c-b7fb880733eb"
total_cost
0.000395415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
191
wordsDialogue
191
55.9718%