NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-19-01KACPR4ST1H9VQCH4JFWC3103
Run Details
Model:
Gemini 3 Pro (Preview)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
13.0s
Cost:
$0.018916
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
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 heavy rain pounded against the cracked pavement where the motionless body lay cold under the single flickering yellow streetlamp. Detective Miller adjusted his soaked fedora before kneeling down to examine the silver knife sticking out of the victim's chest. Dark crimson blood swirled slowly with the muddy water, creating a gruesome pattern that stained the expensive Italian leather shoes. A sudden noise from the alleyway caused Miller to turn his head toward the shadows lurking behind the rusted dumpster. He realized quickly that this calculated murder was not a simple robbery gone wrong but a message sending a warning.
created_at
"2025-11-19T00:03:21.834005+00:00"
11/19/2025, 12:03:21 AM
model
"google/gemini-3-pro-preview-20251117"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2208
moderation_latency
(null)
generation_time
12430
tokens_prompt
42
tokens_completion
530
native_tokens_prompt
38
native_tokens_completion
1570
native_tokens_completion_images
0
native_tokens_reasoning
1454
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
0.018916
api_type
"completions"
id
"gen-1763510588-zOoijOKqSVsA6v1Aj4uR"
upstream_id
(null)
total_cost
0.018916
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
20
2
20
3
20
4
20