NC Bench
Overview
About
Tests
Models
Model
Llama 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35T0EB5SWWFPSYMNGTN7GAH
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 poured over the blueprints of the children's party venue, her brow furrowed in concentration. Bill lounged on the couch behind her, snacking on a bag of potato chips. "Okay, so we've got three entrances, two of which have security cameras," Molly said, tapping her pen on the coffee table. "We can take out the east entrance with a simple masking tape job, but the west entrance has a live guard." Bill crunched on a chip, "I'm on it. I've got a great 'lost puppy' routine that'll distract him for at least five minutes." Molly raised an eyebrow. "You're going to use a puppy to distract a security guard?" "Not just any puppy, Molly. I've got a python in a puppy costume. It's a game-changer." Molly shook her head, "You're a genius, Bill. And a little bit insane." "Hey, it's not insane if it works. Now, what's the plan for once we're inside?" "Chaos," Molly said with a grin. "We create a diversion, grab the presents, and get out. We'll be in and out in ten minutes, tops." Bill high-fived the air, "It's going to be the greatest heist this side of the sandbox!"
id
"gen-TBpf5YbDJBnD5oQntw2ubpOzeExC"
total_cost
0.000262395
upstream_id
"cmpl-5103809ead5b46439ea3e786bc12b55e"
created_at
"2024-07-19T15:33:18.425233+00:00"
Friday, July 19th, 2024 at 3:33:18 PM GMT+00:00
model
"meta-llama/llama-3-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"OctoAI"
latency
4364
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
271
native_tokens_prompt
72
native_tokens_completion
271
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000262395
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
196
0.0003%
Dialogue to Total Word Ratio
Ratio: 68.88%, Deviation: 18.88%
neededClean
false
wordsTotal
196
wordsDialogue
135
49.8723%