NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5XAZHTDZZ139YA08PHYCE
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
5.1s
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
**Opening Scene:** Rain tapped the window like a ghost counting secrets slowly. Detective Harlan Voss stared at the body, cold and still. A single crimson rose lay beside the victim’s pale hand. The room smelled of old books and something far darker. No forced entry, no struggle—just silence and a missing knife. Voss knelt, counting ten perfect fingerprints on the dusty floor. The victim’s eyes were open, frozen in silent, endless surprise. A pocket watch ticked loudly, mocking the stillness of death. Someone had known this room, this moment, this exact betrayal. And now Voss had ten words to unravel the truth.
created_at
"2026-02-16T21:32:46.606144+00:00"
2/16/2026, 9:32:46 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1127
moderation_latency
(null)
generation_time
5013
tokens_prompt
46
tokens_completion
171
native_tokens_prompt
38
native_tokens_completion
145
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
0.0002037
router
(null)
provider_responses
0
id
"9d91f108112294828a54dfbbce30de45"
status
200
is_byok
false
latency
1127
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277560-Gfd5BTJg9mwL0D2sY6a7"
upstream_id
"9d91f108112294828a54dfbbce30de45"
total_cost
0.0002037
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
88.5529%
Matches word count
n/a
neededClean
false
sentences
11
wordCounts
0
2
1
10
2
10
3
10
4
10
5
11
6
10
7
10
8
10
9
10
10
10