NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-23-01J3G819CABN08AJN2HBT6A9FH
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 scribbled on a cocktail napkin, her eyes fixed on the crude layout of the children's party venue. "Alright, so we sneak in through the 'Petting Zoo' entrance, avoid Mrs. Jenkins' watchful gaze by the bouncy castle, and then make a beeline for the gift table." Bill shook out a peanut from its shell and popped it into his mouth. "What about the balloons? They're blocking the view." Molly rolled her eyes. "We'll just create a diversion. Make like we're part of the piñata-breaking ceremony. Chaos, confetti – guaranteed to draw off the adults." Bill chuckled, crumbs spilling down his chin. "You know, for a professional cat burglar, you have a flair for the absurd." Molly smiled, teeth glinting in the fluorescent lighting. "Hey, someone's got to keep things light in this line of work." Bill snagged the cocktail napkin, scrutinizing the rough map. "And what's with all these exclamation points? You're not exactly selling me on the subtlety of this operation." Molly shrugged, snatching the napkin back. "Hey, when you're stealing presents from screaming six-year-olds, 'Stealthy Heist' is not exactly a viable alternative."
id
"gen-OCfT8TTyjmGmVXMakQLYtsOk0bjl"
total_cost
0.0000682
upstream_id
"648b49ce-7bbe-4c1e-bb20-19d0951e74e5"
created_at
"2024-07-23T16:50:47.172838+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
995
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
269
native_tokens_prompt
70
native_tokens_completion
271
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000682
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
1.1793%
Dialogue to Total Word Ratio
Ratio: 64.52%, Deviation: 14.52%
neededClean
false
wordsTotal
186
wordsDialogue
120
34.6408%