NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2GMQMN2JRG9Y92VV5FQBYH
Run Details
Model:
DeepSeek V4 Pro
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
7.9s
Cost:
$0.000217
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
11.71%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The old Victorian house stood silent and empty beneath a heavy, bruise-colored evening sky this Tuesday. Detective Inspector Miles began to whistle a tuneless song as his worn shoes crunched on the gravel. A single pale light burned behind the parlor’s thick velvet curtains, defying the deepening dusk outside. He found the front door already slightly ajar, its brass handle smeared with a dark, wet stain. Inside, the grandfather clock ticked on stubbornly, marking seconds that no living person seemed to count. A woman’s body lay crumpled on the Persian rug, one hand still clutching a shattered crystal champagne flute. Her unblinking eyes stared up at the ornate ceiling, frozen forever in a moment of pure, refined terror. There was no sign of a struggle anywhere else in the perfectly ordered, dustless, and obsessively neat room. A single red rose rested on the marble mantelpiece, its stem wrapped tightly in a black satin ribbon. Miles did not touch the rose, for he understood at once it was not a tribute but a signature.
created_at
"2026-04-25T14:28:04.377Z"
4/25/2026, 2:28:04 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1134
moderation_latency
(null)
generation_time
7820
tokens_prompt
46
tokens_completion
272
native_tokens_prompt
39
native_tokens_completion
230
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.000217065
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"8014bad5-59ae-4f49-b0ec-0ef46c7a3482"
is_byok
false
latency
512
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-1777127284-XtQrHcAagrndirFR8beT"
session_id
(null)
api_type
"completions"
id
"gen-1777127284-RAZh2TTwwsiH0SRc3P41"
upstream_id
"8014bad5-59ae-4f49-b0ec-0ef46c7a3482"
total_cost
0.000217065
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
11.71%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
16
1
17
2
16
3
17
4
16
5
18
6
18
7
18
8
18
9
19