NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5ZAF8MD62YNXVNPEJXR1Z
Run Details
Model:
DeepSeek V3.2
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
4.4s
Cost:
$0.000064
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 midnight with a hollow, metallic finality. Detective Aris Thorne hated these pretentious, overwrought charity galas deeply. His polished shoes clicked across the marble floor impatiently. A single, sharp scream then sliced through the lively chatter. It came from the library, behind the ornate oak doors. He found the hostess slumped over her priceless walnut desk. A jeweled letter opener protruded from her back, glittering coldly. The French windows were open to the stormy night beyond. Only the portrait’s eyes witnessed the act, and they lied. Everyone outside this room was a suspect, including her husband.
created_at
"2026-02-16T21:33:50.694315+00:00"
2/16/2026, 9:33:50 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1056
moderation_latency
(null)
generation_time
4365
tokens_prompt
46
tokens_completion
172
native_tokens_prompt
39
native_tokens_completion
141
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
0.00006372
router
(null)
provider_responses
0
id
"67ac2d6528c541589e543ce675b7d563"
status
200
is_byok
false
latency
1056
endpoint_id
"3570a950-b80f-4acd-bb92-8e1c1c51fafc"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277625-VUjGeDpiICVuU0oxoIDn"
upstream_id
"67ac2d6528c541589e543ce675b7d563"
total_cost
0.00006372
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
97.4082%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
10
2
9
3
10
4
10
5
10
6
10
7
10
8
10
9
10