NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5YMY2N70R651XJ68Q2TVA
Run Details
Model:
DeepSeek V3.1
Test:
N-Length Sentences
Scenario:
Write sentences with 5 words each
Duration:
12.8s
Cost:
$0.000133
Provider:
SambaNova
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 5 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
A cold October rain fell. Detective John Miller arrived late. Another body in the alley. The scene was brutally familiar. A single knife wound. Precise, efficient, and deeply personal. The victim was a man. Early forties, well-dressed, seemingly prosperous. His wallet was still present. His watch glinted under floodlights. No obvious signs of struggle. Miller crouched by the body. He noted the clean cut. A professional’s work, he thought. But something felt strangely off. A playing card lay nearby. The queen of hearts, placed. It was not there before. He was sure of it. This was a new message. A direct challenge for him. The rain began washing evidence. Miller’s team worked around him. He stood up, feeling cold. This was just the beginning.
created_at
"2026-02-16T21:33:37.443698+00:00"
2/16/2026, 9:33:37 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1159
moderation_latency
(null)
generation_time
12757
tokens_prompt
65
tokens_completion
207
native_tokens_prompt
39
native_tokens_completion
170
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
0.00013335
router
(null)
provider_responses
0
id
"d020c8b1-5513-4339-8a8a-9b17e420c50c"
status
200
is_byok
false
latency
1159
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277603-IlTRCBvddJqDO6JiIQ38"
upstream_id
"d020c8b1-5513-4339-8a8a-9b17e420c50c"
total_cost
0.00013335
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
98.2304%
Matches word count
n/a
neededClean
false
sentences
25
wordCounts
0
5
1
5
2
5
3
5
4
4
5
5
6
5
7
6
8
5
9
5
10
5
11
5
12
5
13
5
14
5
15
5
16
5
17
5
18
5
19
5
20
5
21
5
22
5
23
5
24
5