NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-10-16-01JABHXHMP2ZJ0HN02S9F8CPW7
Run Details
Model:
Llama 3.1 Nemotron 70B
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
9.1s
Cost:
$0.000093
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
29.24%
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
Here is the opening scene of a murder mystery with each sentence having exactly 20 words: Detective Jameson stood at the grand estate's entrance, surveying the manicured lawn and tranquil fountain, an eerie contrast to expected chaos within. The once-clear morning sky had transformed into a dreary grey, mirroring the somber mood that shrouded the gathering of esteemed guests nearby. A chill ran down Jameson's spine as he gazed up at the mansion's ornate facade, its beauty now tainted by death's presence. Uniformed officers were already processing the scene, their hushed conversations and deliberate movements a stark juxtaposition to the night's intended festivities. Jameson's eyes met those of his trusted partner, Detective Rodriguez, who stood by the open front door, her expression grim and forewarning. The sound of muffled sobs and anxious murmurs drifted out, foreshadowing the complex web of secrets and lies to be unraveled.
id
"gen-1729112229-uLG71vEIRac217AVeo1f"
upstream_id
"cmpl-RXEEcz6WVy0sB07IEjCQYReG"
total_cost
0.00009335
cache_discount
(null)
created_at
"2024-10-16T20:57:19.211189+00:00"
10/16/2024, 8:57:19 PM
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
170
moderation_latency
(null)
generation_time
8772
finish_reason
"stop"
tokens_prompt
76
tokens_completion
194
native_tokens_prompt
45
native_tokens_completion
194
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00009335
Evaluation details
Result
Evaluator
Details
Meta Data
29.24%
Matches word count
n/a
neededClean
true
sentences
6
wordCounts
0
22
1
22
2
22
3
21
4
22
5
21