NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Flash Lite
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2025-11-18-01KACP8RRC1TTHN63J4MWANYYV
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 old mansion stood silent under a bruised and unforgiving twilight sky. Rain lashed down angrily against the stained glass windows lining the imposing hall. A faint, metallic scent of something dark and disturbing hung heavy within the air. Lord Ashworth lay sprawled unnaturally across the Persian rug, his eyes wide and unseeing. Detective Harding surveyed the opulent, yet strangely unsettling, scene before his weary gaze. A single, ornate letter opener protruded from his chest, a crimson stain blooming outward. No signs of forced entry hinted at the intruder's method of gaining access. Footprints, faint but undeniable, marred the otherwise pristine polished wooden floorboards here. Silence reigned supreme, broken only by the storm’s distant, mournful sighing.
created_at
"2025-11-18T23:54:45.863385+00:00"
Tuesday, November 18th, 2025 at 11:54:45 PM GMT+00:00
model
"google/gemini-2.5-flash-lite"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
304
moderation_latency
(null)
generation_time
1023
tokens_prompt
42
tokens_completion
163
native_tokens_prompt
38
native_tokens_completion
159
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
0.0000674
api_type
"completions"
id
"gen-1763510084-saBtQt4AJtS1Y6lbfGtI"
upstream_id
(null)
total_cost
0.0000674
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
12
1
13
2
14
3
14
4
13
5
14
6
13
7
12
8
11