NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 500 words with 70% dialogue
Run ID
2024-07-23-01J3G7ZQYNKPAGCX9A1S352Y2K
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 cackled as she poured herself a vodka from the mini-fridge. Bill sat on the couch, sipping his coffee and staring at the crime scene tape of a perfectly good pizza that had been left in the break room. "I'm telling you, Molly, this is our best score yet," Bill said, licking his lips. "Who wouldn't want to steal Christmas presents from a bunch of screaming children?" Molly snatched the phone off the coffee table and dialed a number. "Hello, Party Palace? Yeah, I'd like to reserve a 10 a.m. table for 12 bawling kids. No, we don't need any noise-activated toys. And definitely no magic shows. Got it." Bill raised an eyebrow as Molly hung up the phone. "You really think a 10 a.m. birthday party is going to be the most lucrative gig we'll ever hit?" Molly winked at him. "You don't understand the genius of my plan, Bill. We're not just taking presents. We're taking the ultimate cash cow: the birthday list. Think about it: one kid's entire social calendar for the next year is wrapped up in a neatly alphabetized list and written in Sharpie. We're looking at thousands of dollars in gift cards and toys. And as long as we get in and out before the cake is served, we won't even have to deal with the whole 'angry mob of sugar-high children' thing." Bill shook his head, a grin spreading across his face. "You're something else, Molly." "Hey, it's all about maximizing our mark's emotional vulnerabilities," she said, snagging a crumpled up piece of paper from the floor. "I've been studying the etiquette books, Bill. We need to blend in as the 'fun uncles who wear bright sweaters.'" He took the paper from her and scanned it. " 'Men of a certain age wear pleated pants for parties, provided they are accompanied by a woman of discerning fashion sense'?" Molly nodded, eyes narrowed. "Exactly. We'll look more plausible if we're both wearing pleated pants and flashing fake smiles like we're trying to seduce the Easter Bunny." Bill choked on his coffee, nearly spitting it out the back of his throat. "You're seriously suggesting we disguise ourselves as an elderly couple at a children's party?" Molly's smile grew wider. "I'm not suggesting it, Bill. I'm proposing it. And think about it, we'll be so undercover, no one will suspect a thing...until we're making off with all the Wii games and building sets." He wiped the coffee off his shirt and tossed the crumpled paper back onto the floor. "You know, sometimes I wonder how we make a living." Molly cackled again and tossed back another shot. "Because we're the greatest thieves the world has ever seen, Bill. The greatest."
id
"gen-6J4v2gufMDrlsTrkCX6WtSR49nTl"
total_cost
0.000136
upstream_id
"d9b28c2e-2cc9-4f09-a67f-2154b5c4ab0e"
created_at
"2024-07-23T16:49:57.997355+00:00"
Tuesday, July 23rd, 2024 at 4:49:57 PM GMT+00:00
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
2478
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
608
native_tokens_prompt
70
native_tokens_completion
610
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000136
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
456
73.9611%
Dialogue to Total Word Ratio
Ratio: 67.54%, Deviation: 2.46%
neededClean
false
wordsTotal
456
wordsDialogue
308
36.9805%