NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-23-01J3G819PJ07SG81SYFVT7NMB8
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 the wig, a bright pink monstrosity with a bow that seemed to be perpetually askew. Bill, resplendent in a yellow t-shirt with a cartoon character emblazoned on it, eyed her warily. "You know, Molly, we've pulled off some big scores in our time," he said, "but this one takes the cake. Or rather, the mediocre birthday cake with the sad, store-bought ice cream." Molly snorted. "Hey, don't knock the ice cream. It's the perfect getaway food." Bill raised an eyebrow. "You're going to eat a brick of generic ice cream right before a high-pressure heist? You're a genius, girl." They were standing in front of the children's party, located in a cramped, windowless room above a tattoo parlor. The sound of shrieking kids and tinny muzak drifted out from within. "Okay, here's the plan," Molly said, unfolding a scribbled-on map. "You create a diversion at the birthday boy's cake-eating ritual while I slip into the presents and grab as many as I can carry." Bill nodded, a glint in his eye. "You know, for a smart thief, I always forget the part where you get caught up in the mosh pit of overexcited seven-year-olds." Molly grinned, a plan already forming in her mind. "That's the beauty of it, Bill. You're going to be the one getting covered in glitter and sweat."
id
"gen-u9qTNqmomKerJ40cFKvWpu98rV7Y"
total_cost
0.0000776
upstream_id
"01388984-2346-44ed-9f6e-fb7b9530f28c"
created_at
"2024-07-23T16:50:47.793931+00:00"
Tuesday, July 23rd, 2024 at 4:50:47 PM GMT+00:00
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
1322
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
317
native_tokens_prompt
70
native_tokens_completion
318
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000776
Evaluation details
Result
Evaluator
Details
Meta Data
0.0848%
Matches word count
n/a
neededClean
false
words
229
0.0000%
Dialogue to Total Word Ratio
Ratio: 58.52%, Deviation: 48.52%
neededClean
false
wordsTotal
229
wordsDialogue
134
0.0424%