NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5BXXV1J0WVCW17H5S6FN9
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
6.1s
Cost:
$0.000226
Provider:
Nebius
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 rain fell hard on the old, cobbled street. Detective Clarke sighed, staring at the bloodstained doorstep. A single glove lay crumpled near the victim’s feet. The flickering lamplight cast long shadows across the scene. She knelt, examining the knife wedged between two bricks. A faint whisper of perfume lingered in the damp air. The victim’s face was frozen in silent, wide-eyed horror. Clarke’s notebook filled with quick, precise sketches and notes. A distant clock struck midnight, its chime eerily hollow. Something about this case felt wrong, deeply and unnaturally.
created_at
"2026-02-16T21:23:17.01331+00:00"
2/16/2026, 9:23:17 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
436
moderation_latency
(null)
generation_time
6034
tokens_prompt
46
tokens_completion
158
native_tokens_prompt
41
native_tokens_completion
137
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
0.000226
router
(null)
provider_responses
0
id
"chatcmpl-aab8970ebe7a81d7"
status
200
is_byok
false
latency
436
endpoint_id
"09c158fc-63e9-4c3a-813e-c952828ac296"
provider_name
"Nebius"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771276990-PAJE3SqSeM84pLavh4dS"
upstream_id
"chatcmpl-aab8970ebe7a81d7"
total_cost
0.000226
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Nebius"
Evaluation details
Result
Evaluator
Details
Meta Data
74.8692%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
8
2
9
3
9
4
9
5
10
6
10
7
9
8
9
9
9