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
2025-11-18-01KACP6WZ11JW3ED8AAPWGNYYB
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
A chilling November wind howled mournfully through the skeletal branches of the ancient oak trees. Detective Miles Corbin surveyed the desolate scene with a practiced, weary gaze this dismal evening. Inside the grand, decaying mansion, a prominent philanthropist lay tragically dead upon the Persian rug. His lifeless eyes stared blankly upwards, reflecting the opulent but now somber surroundings surrounding him. A single, crimson stain marred the pristine white of his expensive silk smoking jacket. Inspector Davies examined the ornate desk, searching for any clue left by the elusive perpetrator. Shadows danced eerily in the flickering lamplight, obscuring vital details for the investigation. The oppressive silence of the drawing-room amplified the detective's growing sense of unease here.
created_at
"2025-11-18T23:53:44.778643+00:00"
Tuesday, November 18th, 2025 at 11:53:44 PM GMT+00:00
model
"google/gemini-2.5-flash-lite"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
286
moderation_latency
(null)
generation_time
904
tokens_prompt
42
tokens_completion
160
native_tokens_prompt
38
native_tokens_completion
153
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
0.000065
api_type
"completions"
id
"gen-1763510023-6dBE0hCQcwbtmwSHOSgn"
upstream_id
(null)
total_cost
0.000065
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0003%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
15
1
15
2
15
3
15
4
14
5
15
6
13
7
15