NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5YRCH06A92ERR38KF2Z1P
Run Details
Model:
DeepSeek V3.1
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
10.8s
Cost:
$0.000099
Provider:
SambaNova
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
Detective Miles arrived at the grim scene before dawn. The mansion stood silent, holding its breath around us. We found the body in the opulent library. Lord Ashworth lay dead on the Persian rug. A single, silver dagger protruded from his chest. No forced entry, no obvious signs of struggle. The large french windows were still securely locked. His cold tea sat untouched beside him. Every detail suggested a calm, domestic evening. So why did my skin begin to crawl? Each perfectly placed object felt suddenly sinister. Everyone in the house is a suspect now. But which one of them is the killer?
created_at
"2026-02-16T21:33:38.494271+00:00"
2/16/2026, 9:33:38 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1254
moderation_latency
(null)
generation_time
10812
tokens_prompt
65
tokens_completion
150
native_tokens_prompt
39
native_tokens_completion
124
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
0.00009885
router
(null)
provider_responses
0
id
"4afe604a-7abb-438e-8890-aa2f4fe72f48"
status
200
is_byok
false
latency
1252
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277607-uMK4nhLC2W7omuyK6w9B"
upstream_id
"4afe604a-7abb-438e-8890-aa2f4fe72f48"
total_cost
0.00009885
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
31.4831%
Matches word count
n/a
neededClean
false
sentences
13
wordCounts
0
9
1
9
2
8
3
8
4
8
5
8
6
8
7
7
8
7
9
8
10
7
11
8
12
8