NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5VC4B4CYRDGJYJ17VWVJK
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
8.9s
Cost:
$0.000304
Provider:
Novita
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The fog clung to the cobblestones like a shroud, silent and thick beneath the flickering gaslight. A distant clock struck twelve, its chimes hollow in the empty street, echoing between the narrow brick walls. The detective’s coat flapped as he turned the corner, his breath visible in the cold, his eyes sharp with suspicion. A single glove lay abandoned near the gutter, its fingers curled as if clutching some unseen terror, stained dark. The body sprawled in the alleyway, pale and still, a knife protruding from its chest, glinting under the moonlight. A note fluttered in the wind, pinned beneath the victim’s hand, its message clear but cryptic: *He knows the truth.* The detective knelt, his gloves brushing the victim’s wrist, finding no pulse, only the chill of death and secrets. Shadows shifted in the windows above, faces peering down, then vanishing, as if the night itself held its breath. The killer was close, watching, waiting—perhaps even smiling—as the game began anew, with blood as its first move.
created_at
"2026-02-16T21:31:46.326671+00:00"
2/16/2026, 9:31:46 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1735
moderation_latency
(null)
generation_time
8730
tokens_prompt
46
tokens_completion
259
native_tokens_prompt
38
native_tokens_completion
222
native_tokens_completion_images
0
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
0.0003038
router
(null)
provider_responses
0
id
"c9863fc55c8b2bee97684abab81f10fc"
status
200
is_byok
false
latency
1735
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277496-WbKgeVNdiLjAajMbqv00"
upstream_id
"c9863fc55c8b2bee97684abab81f10fc"
total_cost
0.0003038
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
49.4408%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
16
1
18
2
20
3
19
4
19
5
39
6
19
7
20