NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5Q69XA0SMPQB8RQQ78HRY
Run Details
Model:
DeepSeek V3.2
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
8.6s
Cost:
$0.000103
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
Detective Arlo Finch studied the impossible crime scene. The library doors had been locked from the inside. A single dagger protruded from the victim's motionless chest. Yet there was no trace of the murderer's presence. Lord Blackwood sat perfectly still in his leather armchair. His empty eyes reflected the fire's dying, desperate glow. No windows were broken; the chimney was far too narrow. The floor showed no footprints besides their own. Every book remained upon its shelf, neat and orderly. The only disturbance was a fallen chess piece. A black queen rested near the victim's right shoe. This was, without any doubt, a perfect locked room. Finch carefully picked up the queen with gloved fingers. He detected a faint, unfamiliar scent of bitter almonds. "Poison, as well," he murmured to his silent partner. The puzzle now had two distinct, contradictory methods. Someone had executed an utterly flawless, theatrical murder. But every perfect crime must contain a single flaw. Detective Finch began his search for that tiny error.
created_at
"2026-02-16T21:29:28.49045+00:00"
2/16/2026, 9:29:28 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1111
moderation_latency
(null)
generation_time
8572
tokens_prompt
46
tokens_completion
283
native_tokens_prompt
39
native_tokens_completion
231
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
0.000102891
router
(null)
provider_responses
0
id
"7bc8b764171b5879079819062a56720e"
status
200
is_byok
false
latency
1111
endpoint_id
"8a5fb6d3-ef71-4958-af54-269ffa3a3c6e"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277359-sZcRI2DRuA1wONXxz9Ip"
upstream_id
"7bc8b764171b5879079819062a56720e"
total_cost
0.000102891
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
59.3871%
Matches word count
n/a
neededClean
false
sentences
20
wordCounts
0
8
1
9
2
9
3
9
4
9
5
9
6
9
7
1
8
8
9
9
10
8
11
9
12
9
13
9
14
9
15
9
16
8
17
8
18
9
19
9