NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 500 words with 70% dialogue
Run ID
2024-09-26-01J8PZ2QAS7XEAJZHN41RDJSP7
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 adjusted her wig, a fluffy pink monstrosity that she hoped would distract from her scar above her left eyebrow. "Alright, here's the plan. We hit the party at 3pm, when the kids are all occupied with cake and ice cream. We go in through the back door, avoiding the one with the obligatory ' Parents' Only' sign. We make a beeline for the gift tables, and then we're out, with presents in hand." Bill rubbed his hands together, excitement radiating from his pores. "Sounds like a cakewalk. What makes you think the birthday boy's got all the big-ticket items? Gold chains, Rolexes?" Molly winked. "I overheard the birthday girl's mom mentioning a 'very special delivery' from her aunt in New York. I'm betting it's something worth the trouble. Besides, I've got my eye on the perfect disguise. I'll just blend right in with the piƱata-avoiding parents." Bill chuckled. "You're a real ham. Alright, let's assume the worst: the presents are actually just onesies and socks. How much do you estimate we'll net?" Molly consulted a messy notebook, jotting notes in a scribbled handwriting. "If we take all the smaller presents, we're looking at, oh, about five hundred dollars in used Groupons and what passes for 'preppy tchotchkes' around here." Bill whistled. "That's not bad, but I was thinking more along the lines of laptops, credit cards..." Molly held up a hand, grinning mischievously. "We're hitting a kid's party, Bill. These parents are more concerned with getting the kids home before the glow-in-the-dark party starts than with keeping track of their loot. They'll barely notice the millions we haul out of here." Bill scrunched up his face, incredulous. "You're not planning on breaking into the whole neighborhood, are you?" Molly shrugged. "You never know. What if we get to the 'very special delivery' and it's not just a few onesies? Who's going to know? The neighbors will think the pizza guy came early and the party never existed." Bill shook his head, though he couldn't help grinning. "You're going to get us caught." Molly's grin broadened. "I love a good challenge. Besides, it's not every day we get to relive our glory days as expert pickpockets in a glittery jumpsuit." Their respective costumes took shape around them, including Bill's ill-fitting Spiderman suit and Molly's outrageous Mickey Mouse ears. They nodded and held hands, looking identical if not identically stylish outfits. Molly winked, a glint in her eye. "It's settled then. 3pm, back door, gifts and glory await. When's the party planning committee due home?"
id
"gen-o9l87dv4DkEOqH5YCdrppZx257um"
total_cost
0.000068
upstream_id
"bc02e982-e325-429d-a19b-9626afb5c234"
created_at
"2024-09-26T10:49:08.473792+00:00"
Thursday, September 26th, 2024 at 10:49:08 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
115
moderation_latency
(null)
generation_time
2317
finish_reason
"stop"
tokens_prompt
102
tokens_completion
607
native_tokens_prompt
71
native_tokens_completion
609
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000068
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
429
46.8751%
Dialogue to Total Word Ratio
Ratio: 73.89%, Deviation: 3.89%
neededClean
false
wordsTotal
429
wordsDialogue
317
23.4375%