NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2JW1AMXJ5NXVEJ22YFQ6Z2
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
3m 47s
Cost:
$0.043135
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 dark stormy night concealed the old manor's crumbling walls and the gaslight flickering weakly within its many ancient windows. Detective Harper arrived alone, his trench coat drenched, and he squinted through the downpour at the very imposing oak door. He immediately noticed the faint smell of blood, a coppery tang that hung in the air despite the cleansing rain. The massive oak door slowly creaked open before he could knock, revealing a dimly lit foyer with a flickering chandelier. A silent butler slowly gestured him inside, his face pale and completely expressionless, as if carefully carved from old wax. Harper followed the butler down a very long corridor lined with portraits of ancestors with stern faces in gilded frames. The air grew much colder as they approached the library, where a single body lay sprawled on the polished floor. A single brass candelabra sputtered on the desk, casting many dancing shadows over the deceased gentleman's terribly distorted pale visage. Harper slowly kneeled beside the corpse, carefully observing the deep wound on its neck and the strange symbol drawn nearby. The butler whispered softly that the victim was Lord Ashworth, and the murder weapon remained completely unknown to anyone here.
created_at
"2026-04-25T15:07:00.823Z"
4/25/2026, 3:07:00 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3201
moderation_latency
(null)
generation_time
226759
tokens_prompt
46
tokens_completion
8562
native_tokens_prompt
118
native_tokens_completion
9747
native_tokens_completion_images
(null)
native_tokens_reasoning
8250
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
0.0431346
router
(null)
provider_responses
0
endpoint_id
"13bda129-f8a6-4a60-b1db-98082e5f7ccd"
id
"ogZrq2N-2dTqGa-9f1e414240138acf"
is_byok
false
latency
3201
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777129620-faOUNfZbAzp5cp6R1GXT"
session_id
(null)
api_type
"completions"
id
"gen-1777129620-Jgy4BJcXuX1DGLMoEiUB"
upstream_id
"ogZrq2N-2dTqGa-9f1e414240138acf"
total_cost
0.0431346
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20
8
20
9
20