NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DQS75P9QNRD2C7GZ9TWG5
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.2s
Cost:
$0.000468
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
63.6358%
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
“Pass me the glitter glue, Bill. It’s integral.” “Molly, we’re casing a five-year-old’s unicorn rave, not crafting.” “Precisely. We infiltrate as the face-painting professionals. You’ll be Sparkles the Clown. I’ll be Pixie Molar, the Tooth Fairy’s edgy sister with a haversack for presents.” “A haversack? They’ll spot us. The piñata hasn’t even been beaten to a pulp yet and a shifty fairy is stuffing gift bags into a sack?” “That’s your contribution? Criticism? I’m wearing a tutu made of garbage bags, Bill. Commitment. We waltz in during the ‘Happy Birthday’ crescendo. The sonic boom of off-key warbling is our audio camouflage.” “Right, and then what? I pretend to tie a balloon animal and you start hoovering up LEGO sets?” “Don’t be drab. You’ll inflate a long, tragic poodle. The crowd weeps. I, meanwhile, will announce a Present Inspection Protocol. I’ll claim I have to check for ‘contraband broccoli’ and confiscate everything.” “And you think toddlers will buy that?” “Bill, their critical reasoning is mush. I’ll replace the haul with beautifully wrapped boxes of air. By the time they unwrap nothing, we’ll be sipping stolen juice boxes in the getaway minivan.” “The getaway minivan you’ve painted to look like a bouncy castle on wheels.” “You see? You do understand the poetry.”
created_at
"2026-04-25T13:37:18.571Z"
4/25/2026, 1:37:18 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1026
moderation_latency
(null)
generation_time
15116
tokens_prompt
77
tokens_completion
546
native_tokens_prompt
67
native_tokens_completion
504
native_tokens_completion_images
(null)
native_tokens_reasoning
160
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
0.000467625
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"06850136-eb43-4eb2-bc39-962ca2a9e448"
is_byok
false
latency
297
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-1777124238-rQY2mvxZ6rF0EfnWEKDR"
session_id
(null)
api_type
"completions"
id
"gen-1777124238-AQDJrTrgGQLfJ6MsAw1B"
upstream_id
"06850136-eb43-4eb2-bc39-962ca2a9e448"
total_cost
0.000467625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
214
wordsDialogue
214
63.6358%