NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DPWQXEJS2HTF965EWYMMM
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.4s
Cost:
$0.000419
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
99.93%
Dialogue to Total Word Ratio
(details)
95.2068%
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
"So the target's a bouncy castle full of sugar-addled six-year-olds, and we're after the gift pile?" Bill asked, peering through binoculars at the clown making balloon animals. "That's a high-risk giggle zone." Molly sighed, snatching the binoculars. "Stop casing the clown, you idiot. It's operation 'Pin the Tail on the Loot'. We go in as the premium entertainment." "Premium? I've got stage fright. What if they smell the desperation on me?" Bill whimpered. "I can't even do a decent magic trick." "You're not a magician; you're 'Bill the Balloon Baron'. I'm 'Molly the Face-Painting Monet'. I paint a butterfly on a kid's cheek, you twist a balloon into a shiv, we grab the shiny pile and vanish like their hopes of a pony." "A balloon shiv? That's just pointlessly sad, Molly." Bill shuddered. "What's the signal for chaos?" "The birthday song. When they screech 'Happy Birthday', I'll knock over the juice bar, you yell 'PiƱata emergency!', and in the stampede, we load the haul into the 'Barry the Dancing Bear' costume's backpack." "There's a dancing bear?" Bill asked. "You are the dancing bear," Molly said flatly. "The suit has reinforced pockets and no eye holes. You'll be sweating pure panic in the dark, which is perfect. It muffles your sobbing."
created_at
"2026-04-25T13:36:49.409Z"
4/25/2026, 1:36:49 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
625
moderation_latency
(null)
generation_time
11312
tokens_prompt
77
tokens_completion
477
native_tokens_prompt
67
native_tokens_completion
448
native_tokens_completion_images
(null)
native_tokens_reasoning
134
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
0.000418905
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"35e38e22-74b4-4df1-87c9-706c130a422c"
is_byok
false
latency
266
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-1777124209-zs3JNBPfMP6XQ8ZKOf71"
session_id
(null)
api_type
"completions"
id
"gen-1777124209-LZ6KkrjkG7nxWXLzmbB8"
upstream_id
"35e38e22-74b4-4df1-87c9-706c130a422c"
total_cost
0.000418905
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
99.93%
Dialogue to Total Word Ratio
Ratio: 88.37%, Deviation: 1.63%
neededClean
false
wordsTotal
215
wordsDialogue
190
95.2068%