NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2024-09-26-01J8Q0S2EYVJHCRK3ZBAK6PVZV
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 Jameson stood at the edge of the crime scene, the misty morning fog slowly rising from the ground below. The small town of Ravenswood was shaken, residents whispering rumors of a gruesome discovery in the abandoned mansion nearby quickly. Forensic lights illuminated the entrance, casting an eerie glow on the old stone steps and weathered wooden front door slowly. Crime scene tape strained in the gentle morning breeze, flapping against the freezing metal railings with an ominous repetitive sound. In the foyer, Jameson spotted a figure lying motionless, an antique vase shattered near the victim's lifeless outstretched right hand. Bloodstains marred the polished floor, creating an abstract pattern of violence and chaos in the once elegant entrance hallway freely. Constable Lee stood guard, her eyes locked on Jameson as she tallied evidence labels on the crime scene inventory sheets. Together they entered the darkness of the old mansion, their footsteps echoing with every step they cautiously took freely.
id
"gen-Amf5jjkz2HSAQ13BJ4xSKntTgHtA"
total_cost
0.0001076
upstream_id
"chat-e2fe1fd1850b465cabd553fd70779959"
created_at
"2024-09-26T11:17:14.094824+00:00"
Thursday, September 26th, 2024 at 11:17:14 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
171
moderation_latency
(null)
generation_time
7067
finish_reason
"stop"
tokens_prompt
42
tokens_completion
197
native_tokens_prompt
70
native_tokens_completion
199
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001076
Evaluation details
Result
Evaluator
Details
Meta Data
95.0816%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
19