NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DKWMGC4M0QKATVXHM8Y6P
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.1s
Cost:
$0.000342
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.90%
Dialogue to Total Word Ratio
(details)
49.9486%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 unfolded the crinkled party invitation across the sticky table of their surveillance van, her finger tracing the clown’s smeared grin. Bill squinted through a pair of binoculars at the bouncy castle inflating on the lawn, its garish turrets wobbling with menacing glee. She tapped the map, then whispered, “We enter as the magician’s assistants.” He lowered the binoculars, his face a mask of professional dismay, and replied, “I’m allergic to rabbits, Molly.” She sighed, producing two felt bunny ears from her bag with a flourish, their pink satin lining glinting in the low light. Outside, a piñata swayed like a candy-filled safe. Bill reluctantly took the ears, securing them with a grimace as a remote-controlled dinosaur wailed past the van’s rear doors, its tiny cargo of screaming toddlers spotting them instantly.
created_at
"2026-04-25T13:35:10.998Z"
4/25/2026, 1:35:10 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
955
moderation_latency
(null)
generation_time
11063
tokens_prompt
77
tokens_completion
398
native_tokens_prompt
67
native_tokens_completion
360
native_tokens_completion_images
(null)
native_tokens_reasoning
171
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
0.000342345
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"3b6a406d-b6af-432b-b4f1-dceb1050af2f"
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-1777124111-cIm0SHp9q5ILkMDbvOoQ"
session_id
(null)
api_type
"completions"
id
"gen-1777124111-ydcBERmof34dsIw08FTv"
upstream_id
"3b6a406d-b6af-432b-b4f1-dceb1050af2f"
total_cost
0.000342345
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
132
99.90%
Dialogue to Total Word Ratio
Ratio: 8.21%, Deviation: 1.79%
neededClean
false
wordsTotal
134
wordsDialogue
11
49.9486%