NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FDWEAXSDW7G1110H8YY80
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
23.6s
Cost:
$0.000713
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
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 a crinkled party invitation flat on the sticky diner table. “That’s the target, Bill. Little Timmy Turnbull’s fifth birthday. His parents are obscenely wealthy and criminally trusting.” Bill slurped his milkshake, leaving a chocolate moustache. “Right, so we waltz in dressed as what, a clown and a balloon animal?” “Too obvious. We’re the premium ice-cream vendors.” Molly tapped a schematic drawn in crayon. “This bouncy castle is the present vault. Thirty gifts, minimum. We roll in, scoop the haul into our freezer cart, and roll out during the piñata frenzy.” Bill squinted. “Piñata frenzy? That’s our window?” “Blindfolded toddlers swinging a bat, Bill. No one’s watching a couple of ice-cream thieves.” Bill nodded slowly, then frowned. “What’s our flavour of the day?” “Vanilla distraction and get-away fudge.” Molly leaned in, her voice a conspiratorial whisper. “We just need to navigate the ball-pit gauntlet and avoid the cake-smeared enforcer.” “You mean the birthday boy’s mother.” “She’s a hugger, Bill. A vicious, relentless hugger. It’s the greatest danger we’ll face today. You ready?” Bill wiped his mouth, leaving a smear of chocolate on his sleeve. “For a mountain of plush unicorns and action figures? I was born ready.”
created_at
"2026-04-25T14:06:51.343Z"
4/25/2026, 2:06:51 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1093
moderation_latency
(null)
generation_time
23344
tokens_prompt
77
tokens_completion
757
native_tokens_prompt
67
native_tokens_completion
786
native_tokens_completion_images
(null)
native_tokens_reasoning
462
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
0.000712965
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"9183aba7-945f-4496-a12e-3d7e290e5732"
is_byok
false
latency
367
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-1777126011-PhU2fbMOtDQn7t64BpIt"
session_id
(null)
api_type
"completions"
id
"gen-1777126011-dRxIdDbAoq0ORjR3qSlm"
upstream_id
"9183aba7-945f-4496-a12e-3d7e290e5732"
total_cost
0.000712965
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
0.00%
Dialogue to Total Word Ratio
Ratio: 73.40%, Deviation: 23.40%
neededClean
false
wordsTotal
203
wordsDialogue
149
49.9920%