NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5V779SM0CVW1PTV4Y7QYA
Run Details
Model:
DeepSeek V3.1
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
7.3s
Cost:
$0.000243
Provider:
Novita
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 house stood silent beneath a cold and watchful October moon. Inspector Miles trudged up the gravel path alone, his heavy coat damp with evening dew. His flashlight beam cut a lonely swathe through the oppressive, enveloping darkness ahead. He found the study door slightly ajar, a sliver of ominous yellow light escaping. Inside, Lord Ashworth lay sprawled across his desk, a look of pure surprise. A single, ornate letter opener protruded from his back, its silver hilt gleaming. The inspector noted the precise angle, the lack of any obvious struggle. A stack of papers remained perfectly neat, except for one scattered page. Every book was perfectly aligned on the shelves, every object meticulously dusted. This compulsive orderliness made the single violent act seem even more jarring. Then Miles saw the note, placed deliberately beside the dead man's hand. Its message was simple, just five words typed on a crisp slip. It read: 'The wrong one died tonight, you fool.' This changed everything about the case, suggesting a far deeper conspiracy. Someone had killed with purpose, and they were far from finished yet.
created_at
"2026-02-16T21:31:39.536527+00:00"
2/16/2026, 9:31:39 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1001
moderation_latency
(null)
generation_time
7050
tokens_prompt
65
tokens_completion
284
native_tokens_prompt
40
native_tokens_completion
232
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0002428
router
(null)
provider_responses
0
status
429
is_byok
false
latency
60
endpoint_id
"012f7d1f-23d4-4d03-9aa3-432d8ad82757"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3.1"
1
id
"564962f9-ba99-40d6-8503-cb22e7f7aac9"
status
200
is_byok
false
latency
1001
endpoint_id
"715d05e1-9fa7-4ceb-834a-833f5e26a55a"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277491-uVrZl6CFtbkhFa99wK10"
upstream_id
"564962f9-ba99-40d6-8503-cb22e7f7aac9"
total_cost
0.0002428
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
7.1429%
Matches word count
n/a
neededClean
false
sentences
14
wordCounts
0
13
1
15
2
13
3
14
4
13
5
13
6
12
7
12
8
12
9
12
10
12
11
12
12
20
13
12