NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8Q0P99F1R3YVC63TWVCW7FH
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"I'm telling you, Bill, this is a genius plan," Molly said, grinning mischievously. "Stealing from a kid's party? You think that's genius?" Bill replied, raising an eyebrow. "Come on, it's a smorgasbord of loot in there. iPads, LEGOs, a possible PlayStation or two... we're looking at a haul that'll set us up for months," Molly said, her eyes shining with excitement. "Months? We'll be lucky if we don't end up on a Most Wanted list for ruining a bunch of toddlers' birthdays," Bill countered. "Oh, don't be such a party pooper. We'll be fine. We'll blend in with the parents, maybe even wear some ridiculous outfits to really sell it," Molly suggested. "You mean like that awful 'I'm with Stupid' t-shirt you wore to the zoo job?" Bill asked, chuckling. "Hey, that shirt is a classic! And it worked, didn't it? We made off with a whole bucket of stolen monkey food," Molly said, snickering. "Monkey food? That was the worst score ever. We ended up using it to fertilize my compost heap," Bill said, shaking his head. "Okay, okay, maybe the zoo job wasn't our finest hour. But this one will be different, I promise," Molly said, holding out her pinky for Bill to shake. "I'm only doing this because I love you, moll," Bill said, linking his pinky with hers.
id
"gen-czw4Crzb8y8lXlwoLuS3QJwIdKm0"
total_cost
0.000351
upstream_id
"3c5f6411-a68b-4e7e-ab1e-da635d7f9611"
created_at
"2024-09-26T11:15:45.590897+00:00"
Thursday, September 26th, 2024 at 11:15:45 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
321
moderation_latency
(null)
generation_time
9625
finish_reason
"stop"
tokens_prompt
68
tokens_completion
318
native_tokens_prompt
71
native_tokens_completion
319
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000351
Evaluation details
Result
Evaluator
Details
Meta Data
9.6081%
Matches word count
n/a
neededClean
false
words
222
16.1350%
Dialogue to Total Word Ratio
Ratio: 78.38%, Deviation: 11.62%
neededClean
false
wordsTotal
222
wordsDialogue
174
12.8716%