NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-26-01J8PYWGE39SYE1BENRSG5M0GB
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly leaned back in her chair, eyes fixed on the security footage of the party on the TV screen. "Alright, so we've got one entrance, one exit, and approximately 300 sugar-high kids. What's the plan?" Bill scratched his chin, his pinky ring glinting in the dim light. "I was thinking we pose as bounce-house staff and work our way in. Easy peasy." Molly snorted. "Pose? You can barely contain your excitement at the thought of a trampoline for toddlers. We'll be seen coming a mile away." "Hey, I resent that. I'm a professional. I can totally keep a straight face while simultaneously thinking about all the loot we'll be scoring." Bill grinned. "Bingo halls, amusement parks, kids' birthday parties... name an establishment with a room full of unsupervised riches, and I'm there." Molly chuckled, her eyes wandering to the "Spare the Rod" pamphlet on Bill's coffee table. "Your passion for larceny is admirable, but have you looked at the 'dos and don'ts' list on the party invitation? 'No climbing the walls!' 'No throwing balloons!'... 'No eating the birthday cake!' What kind of party is this, anyway?" Bill shrugged, mouth full of popcorn. "I heard the kid's mom is a 'Pinterest Parent.' You can tell by the excessive use of glitter and macrame."
id
"gen-QoddLrWaVX23f719Y4Njb0NmQ9ZP"
total_cost
0.0000738
upstream_id
"4a4e517b-a513-4f39-906c-c6f46d10e5ca"
created_at
"2024-09-26T10:44:05.015594+00:00"
Thursday, September 26th, 2024 at 10:44:05 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
250
moderation_latency
(null)
generation_time
2451
finish_reason
"stop"
tokens_prompt
68
tokens_completion
297
native_tokens_prompt
71
native_tokens_completion
298
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000738
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
214
0.0000%
Dialogue to Total Word Ratio
Ratio: 75.23%, Deviation: 25.23%
neededClean
false
wordsTotal
214
wordsDialogue
161
34.0511%