NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2025-11-18-01KACPCMXWW45RSME05Z4VEC9Y
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 relentless autumn rain hammered tirelessly against the leaded glass windows of the grand and imposing Ashworth Manor. Detective Inspector Miles Corbin stood silently within the doorway, his keen, observant eyes surveying the chaotic scene before him. The vast library, with its towering shelves of leather-bound books, smelled of old paper, cold ashes, and sharp, bitter regret. Beside the cold, stone fireplace, Lord Ashworth sat slumped lifelessly in his favorite high-backed, crimson leather armchair. An ornate silver letter opener, its beautiful hilt shaped like a snarling griffin, was plunged deep into his chest. On the expensive Persian rug nearby, a delicate porcelain teacup lay shattered into a hundred tiny, glittering shards. Corbin knew with a cold, sinking certainty the killer was still somewhere within the manor’s vast, shadow-filled walls.
created_at
"2025-11-18T23:57:09.524574+00:00"
Tuesday, November 18th, 2025 at 11:57:09 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2598
moderation_latency
(null)
generation_time
17261
tokens_prompt
42
tokens_completion
783
native_tokens_prompt
38
native_tokens_completion
2010
native_tokens_completion_images
0
native_tokens_reasoning
1841
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
0.0201475
api_type
"completions"
id
"gen-1763510211-aV16N1Yep8tk5nmR5mdM"
upstream_id
(null)
total_cost
0.0201475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
40.4590%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
18
1
19
2
21
3
18
4
19
5
18
6
19