NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5ZN5W6V1DWVDEW3HXTBH4
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
4.4s
Cost:
$0.000213
Provider:
Novita
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 fog clung thickly to the cobblestone streets below. A single streetlamp flickered weakly, casting long, shifting shadows. Detective Harlan Mercer adjusted his hat, scanning the silent alleyway. The body lay sprawled, one hand clutching a torn note. Blood pooled darkly around the victim’s chest, stark against pale skin. Mercer knelt, gloved fingers brushing the edge of the damp paper. The message was cryptic, smudged with rain and something darker. Footsteps echoed faintly, then vanished into the night’s oppressive stillness. Someone had watched this murder; Mercer could feel their presence. He pocketed the note, knowing it held the first clue.
created_at
"2026-02-16T21:34:01.830011+00:00"
2/16/2026, 9:34:01 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
797
moderation_latency
(null)
generation_time
4396
tokens_prompt
46
tokens_completion
177
native_tokens_prompt
38
native_tokens_completion
152
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
0.0002128
router
(null)
provider_responses
0
id
"012591882ad32be2a0061c621c83d1ff"
status
200
is_byok
false
latency
797
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277636-xZZiqCaPQRpTICQimQNi"
upstream_id
"012591882ad32be2a0061c621c83d1ff"
total_cost
0.0002128
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
89.6327%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
9
2
10
3
10
4
11
5
11
6
10
7
10
8
10
9
10