NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2025-11-18-01KACP4493JNE44A7FKB04ECJG
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
Detective Harding arrived at the grand manor as the clock struck midnight, while relentless, cold rain lashed against the windows. The butler, a grim statue of a man, showed him silently down the long, shadowed hallway of the old house. He entered the oak-paneled study where a dying fire cast long, dancing shadows across the expensive, ornate leather furniture. Lord Harrington was slumped facedown onto his immense mahogany desk, a single, dark crimson stain spreading across the blotter. An overturned crystal glass lay shattered on the floor beside the desk, its amber contents pooling into the Persian rug. The only sound in the suffocatingly silent room was the grandfather clockâs relentless, metronomic ticking from a far corner. Harding noted the serene, almost peaceful expression on the dead man's face, a detail that felt chillingly out of place.
created_at
"2025-11-18T23:52:28.829331+00:00"
Tuesday, November 18th, 2025 at 11:52:28 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2109
moderation_latency
(null)
generation_time
15768
tokens_prompt
42
tokens_completion
799
native_tokens_prompt
38
native_tokens_completion
1858
native_tokens_completion_images
0
native_tokens_reasoning
1689
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
0.0186275
api_type
"completions"
id
"gen-1763509932-ppAAG6L8sqDHdsBDEXlI"
upstream_id
(null)
total_cost
0.0186275
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
88.7580%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
20
1
20
2
20
3
19
4
20
5
19
6
20