NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2EDZP7DASPK8SJ7RZBK37G
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
6.5s
Cost:
$0.000230
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
88.22%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The old clock struck midnight, its chime echoing hollowly. Rain lashed against the library's tall, frosted window panes. Detective Miles stared down at the body on the floor. A single crimson rose rested upon the victim's still chest. There were no signs of struggle, no overturned furniture nearby. The only clue was a faint scent of jasmine perfume. He knelt, examining the ornate silver locket clutched tightly. Inside, a faded photograph showed a smiling, unfamiliar woman. "Sir, the doors were locked from the inside," said Collins. "Impossible," Miles whispered, "this room has no secret passages." Someone had vanished into thin air, leaving only silent questions.
created_at
"2026-04-25T13:49:26.091Z"
4/25/2026, 1:49:26 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
985
moderation_latency
(null)
generation_time
6437
tokens_prompt
46
tokens_completion
297
native_tokens_prompt
39
native_tokens_completion
245
native_tokens_completion_images
(null)
native_tokens_reasoning
102
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
0.000230115
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"321702d8-8957-4f34-8ac1-ada96ee02b60"
is_byok
false
latency
292
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-1777124966-sbXTJ8JA2CP7e7oulyqa"
session_id
(null)
api_type
"completions"
id
"gen-1777124966-rVEU2Jjt3FEm1SR2nRYF"
upstream_id
"321702d8-8957-4f34-8ac1-ada96ee02b60"
total_cost
0.000230115
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
88.22%
Matches word count
n/a
neededClean
false
sentences
11
wordCounts
0
9
1
9
2
10
3
10
4
10
5
10
6
9
7
9
8
10
9
9
10
10