NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-19-01KACR7YYR3GP3E2WKDBG07JXG
Run Details
Model:
Gemini 3 Pro (Preview)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
10.9s
Cost:
$0.016780
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
80.33%
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
The heavy rain pounded against the dark windows of the old mansion while the wind howled through the cracked stones outside. Lord Harrington lay motionless on the expensive Persian rug with a silver dagger buried deep within his chest near the heart. A single drop of crimson blood slowly trickled down the pale skin of his neck and stained the white collar. Detective Miller stepped into the cold room and carefully adjusted his fedora before glancing at the terrified maid standing nearby. The clock on the mantle had stopped at exactly midnight which suggested that the killer had struck at that precise hour. He knew that tonight would be a long night because everyone in this house had a secret worth killing for.
created_at
"2025-11-19T00:29:26.155262+00:00"
11/19/2025, 12:29:26 AM
model
"google/gemini-3-pro-preview-20251117"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1959
moderation_latency
(null)
generation_time
10826
tokens_prompt
42
tokens_completion
507
native_tokens_prompt
38
native_tokens_completion
1392
native_tokens_completion_images
0
native_tokens_reasoning
1255
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
0.01678
api_type
"completions"
id
"gen-1763512155-oGOtFbrlyJesSDm7OZ3g"
upstream_id
(null)
total_cost
0.01678
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
80.33%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
21
1
21
2
20
3
20
4
21
5
20