NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5V3R8QZAYN4C03TERN15G
Run Details
Model:
DeepSeek V3.2
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
5.2s
Cost:
$0.000061
Provider:
AtlasCloud
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 grand clock struck twelve in the dusty, silent hall. A single scream then pierced the old manor’s deep gloom. We found Lord Blackwood dead beside his spilled brandy glass. A crimson stain slowly spread across his white silk waistcoat. No window was open; the study door had been locked. His cold eyes stared blankly at the painted ceiling above. The butler entered, his face a mask of practiced calm. But his trembling hands betrayed a far more secret fear. Everyone in the house that night had a hidden motive. Only the killer knew which of these ten words mattered.
created_at
"2026-02-16T21:31:33.824731+00:00"
2/16/2026, 9:31:33 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1480
moderation_latency
(null)
generation_time
5125
tokens_prompt
46
tokens_completion
155
native_tokens_prompt
45
native_tokens_completion
130
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
0.0000611
router
(null)
provider_responses
0
id
"adac88244b3b497c97f18ea029794f7a"
status
200
is_byok
false
latency
1480
endpoint_id
"3570a950-b80f-4acd-bb92-8e1c1c51fafc"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277487-gR92rZZ5BuYvJKbY7rdh"
upstream_id
"adac88244b3b497c97f18ea029794f7a"
total_cost
0.0000611
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10