NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM629JP8WWYTB7H7XSJZDY5
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
4.5s
Cost:
$0.000128
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 moon cast cold shadows on the empty street. A distant clock struck twelve with echoing, hollow chimes. Detective Harlan frowned at the body sprawled below. The victim’s face was frozen in silent, wide-eyed terror. Blood pooled darkly around the knife still lodged deep. No footprints marked the damp pavement near the corpse. Harlan’s partner, Reyes, muttered curses under her breath softly. The flickering streetlamp revealed a torn scrap of fabric. Both detectives knew this killer was careful, methodical, cruel. Somewhere in the night, a murderer watched—and smiled darkly.
created_at
"2026-02-16T21:35:28.530958+00:00"
2/16/2026, 9:35:28 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
865
moderation_latency
(null)
generation_time
4453
tokens_prompt
46
tokens_completion
159
native_tokens_prompt
39
native_tokens_completion
136
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
0.000127996
router
(null)
provider_responses
0
id
"8450992e966f4bcbb20511e7c9c113a9"
status
200
is_byok
false
latency
865
endpoint_id
"5bb598f5-fd97-4f8b-91e4-ceab3743a03b"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277723-DnSKiNP407dHfsI5rjRS"
upstream_id
"8450992e966f4bcbb20511e7c9c113a9"
total_cost
0.000127996
cache_discount
1.08e-7
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
74.8692%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
9
2
8
3
10
4
9
5
9
6
9
7
9
8
9
9
10