NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DVXSJE2D5BMXFWENSBE20
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6m 60s
Cost:
$0.018175
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
60.0948%
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 smoothed the glittery invitation across the sticky diner table, shedding sparkles onto a cold plate. "This is a unicorn party, Bill. Presents will be piled high." Bill poked his pink milkshake, a froth mustache forming on his lip. "I hate unicorns. Too sparkly." She tapped a crayon unicorn doodled on the paper invite. "We're going as entertainers. I'll be a fairy; you're a balloon man." He twisted a straw wrapper into a tight coil. "My balloon animals look like tumours." Molly beamed, her gold tooth glinting. "Perfect. Distract them with your grotesque creations while I locate the gifts." Bill's eyes narrowed to suspicious slits. "Then we grab and run?" She pulled a whoopee cushion from her coat with a magician's flourish. "No. Fizzy lifting tablets in the juice. Kid floats, then chaos, we fill the bouncy castle and slip away in the confusion." He leaned closer, a pickle chip forgotten between his fingers. "Will the kid come down?" "Eventually. Probably sticky. The presents won't be." she said, waving a dismissive hand. "You've really lost your mind." Bill muttered, shaking his head. "Years ago. That's why we're successful." She winked at a passing toddler. She slid out of the booth and straightened her crooked fairy wings. "Terribly brilliant. Now practice your tumour snake, and try to make it look festive."
created_at
"2026-04-25T13:39:34.328Z"
4/25/2026, 1:39:34 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
768
moderation_latency
(null)
generation_time
419537
tokens_prompt
77
tokens_completion
16110
native_tokens_prompt
67
native_tokens_completion
20857
native_tokens_completion_images
(null)
native_tokens_reasoning
20537
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
0.018174735
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"ad6d49de-b616-4af0-9e9c-4cad2f27a2e4"
is_byok
false
latency
283
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-1777124374-bKexAkBx0uYCdK155CVT"
session_id
(null)
api_type
"completions"
id
"gen-1777124374-dyWp2zsAqAEjbF9BImbw"
upstream_id
"ad6d49de-b616-4af0-9e9c-4cad2f27a2e4"
total_cost
0.018174735
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
220
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
220
wordsDialogue
110
60.0948%