NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5NXNQZT16N4JBBFX798M4
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
6.3s
Cost:
$0.000204
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 in the damp evening air. Detective Grayson adjusted his hat and sighed into the silence. The body lay sprawled across the steps of the church. Pale fingers curled around a crumpled note, now bloodstained. Grayson knelt, his gloved hands trembling slightly with cold. The victim’s eyes stared blankly at the starless sky. A silver locket gleamed faintly against her torn dress. Footsteps echoed behind him, but Grayson did not turn. "Another one," muttered the coroner, shaking his head grimly.
created_at
"2026-02-16T21:28:44.85915+00:00"
2/16/2026, 9:28:44 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1732
moderation_latency
(null)
generation_time
6233
tokens_prompt
46
tokens_completion
159
native_tokens_prompt
38
native_tokens_completion
145
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
0.0002037
router
(null)
provider_responses
0
id
"e98dff3c186727f573620a14e3c69e07"
status
200
is_byok
false
latency
1732
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277317-5NRkPbqOqHIN3tseFTpu"
upstream_id
"e98dff3c186727f573620a14e3c69e07"
total_cost
0.0002037
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
81.8573%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
10
2
10
3
10
4
9
5
9
6
9
7
9
8
9
9
9