NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5DQZNCV5MCQGNQWEYBRSM
Run Details
Model:
DeepSeek V3.1
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
6.3s
Cost:
$0.000206
Provider:
Novita
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 ornate clock strikes midnight with a hollow, solemn tone. Detective Miles dropped his cigarette, crushing it with his heel. A single light glowed from the mansion's top-floor window. He climbed the stone steps, his breath clouding the cold air. The heavy oak door swung open before he could knock. A pale-faced butler gestured silently, his hands trembling with fear. They proceeded down a long hallway lined with grim portraits. Every shadow seemed to hold its breath as they passed. The library door was ajar, spilling a pool of lantern light. Lord Ashton lay still on the Persian rug, eyes wide. A single crimson stain bloomed across his white silk waistcoat. No weapon was visible in the quiet, book-lined room. The butler finally spoke, his voice a thin, reedy whisper. "He was alone in here for hours, I swear it." Miles knelt, noticing the fragile glass vial immediately. It was empty.
created_at
"2026-02-16T21:24:16.721617+00:00"
2/16/2026, 9:24:16 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1121
moderation_latency
(null)
generation_time
6150
tokens_prompt
65
tokens_completion
235
native_tokens_prompt
40
native_tokens_completion
195
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
0.0002058
router
(null)
provider_responses
0
id
"8672ad22-3d7b-40a8-b7df-3ff3c10a4b27"
status
200
is_byok
false
latency
1121
endpoint_id
"715d05e1-9fa7-4ceb-834a-833f5e26a55a"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277049-E3W4nkZWFvXPOIDoQzai"
upstream_id
"8672ad22-3d7b-40a8-b7df-3ff3c10a4b27"
total_cost
0.0002058
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
84.5228%
Matches word count
n/a
neededClean
false
sentences
16
wordCounts
0
10
1
10
2
10
3
11
4
10
5
11
6
10
7
10
8
11
9
10
10
10
11
10
12
10
13
10
14
8
15
3