NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-18-01KACP857EERQ8CKS0RFBTGN97
Run Details
Model:
Gemini 2.5 Flash Lite
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
929ms
Cost:
$0.000060
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
2.10%
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
Rain lashed against the darkened windowpanes, obscuring the grim tableau within the opulent study. A single ornate lamp cast a pool of sterile light upon the fallen victim. Crimson stained the Persian rug, blooming outwards from the still, vacant form on the polished grandfather clock. Detective Harding’s weary gaze swept the room, searching for any clue overlooked in previous assessments. The air hung heavy with the scent of expensive pipe tobacco and something acrid, distinctly out of place. A half-finished glass of amber liquid sat untouched beside a scattered pile of confidential legal documents. His seasoned instincts screamed that this was no accidental death, but a carefully orchestrated, brutal act.
created_at
"2025-11-18T23:54:25.536803+00:00"
11/18/2025, 11:54:25 PM
model
"google/gemini-2.5-flash-lite"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
217
moderation_latency
(null)
generation_time
852
tokens_prompt
42
tokens_completion
142
native_tokens_prompt
38
native_tokens_completion
140
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
0.0000598
api_type
"completions"
id
"gen-1763510064-tn03IkPQ7cC6d8zkO1WK"
upstream_id
(null)
total_cost
0.0000598
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
2.10%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
14
1
14
2
17
3
15
4
18
5
16
6
16