NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2G105V55FYH1XMRFVHVS7C
Run Details
Model:
DeepSeek V4 Pro
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
8.5s
Cost:
$0.000263
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.13%
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 manor’s library smelled of leather, rain, and candle wax just starting to melt. Inspector Graves studied the body slumped near the hearth, a crimson stain blooming across her chest. Lightning flared outside the tall arched windows, briefly illuminating the room in harsh silver flashes. A single overturned teacup rested on the Persian rug, its amber contents soaking into the wool. “Everyone must remain exactly where they are until we have thoroughly documented this entire scene,” he announced. Lady Winthrop clutched her pearl necklace tightly, her aristocratic face pale as the drawing room’s marble. The butler stood motionless by the service door, his expression unreadable beneath the low candlelight’s glow. Colonel Hughes cleared his throat rather too loudly, his mustache twitching like a startled woodland animal. “I heard no gunshot, no cry, nothing but the storm’s relentless fury battering the windows,” he declared. Graves knelt down carefully beside the deceased, his eyes tracing the curious absence of any weapon. The victim’s right hand was clenched into a fist, except for her index finger, which pointed deliberately. It aimed directly at the towering bookshelf filled with dusty first editions and forgotten family histories. “Would anyone care to explain why such a prominent philanthropist lies murdered before this fireplace?” Graves asked.
created_at
"2026-04-25T14:17:17.759Z"
4/25/2026, 2:17:17 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1309
moderation_latency
(null)
generation_time
8403
tokens_prompt
46
tokens_completion
367
native_tokens_prompt
39
native_tokens_completion
283
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
0.000263175
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"6ca38861-8575-4f61-8c3d-4c12de925335"
is_byok
false
latency
279
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-1777126637-98IkghgL9F1G0Qv5fY70"
session_id
(null)
api_type
"completions"
id
"gen-1777126637-4HCuycvIy4EsHRpOf86C"
upstream_id
"6ca38861-8575-4f61-8c3d-4c12de925335"
total_cost
0.000263175
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.13%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
15
1
16
2
15
3
16
4
33
5
16
6
16
7
50
8
16
9
17