NC Bench
Overview
About
Tests
Models
Model
Llama 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35T5J1J2A3Y6BZ5S54EVD8R
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 unfolded the blueprint of the party venue, a kid's playland on the outskirts of town, and spread it out on the hood of the car. Bill leaned in, his eyes scanning the layout. "Okay, so we've got the bouncy castle, the ball pit, and the snack table. Where's the present stash?" "I'm telling you, it's going to be hidden behind the pinata," Molly said, tapping her finger on the diagram. "It's the only place that makes sense. The kids will be distracted by the sugar rush and the adults will be too busy drinking lukewarm beer to notice us." Bill raised an eyebrow. "You're basing this entire heist on your expert knowledge of children's party protocol?" Molly shrugged. "Hey, I've been to a few in my time. And I've got a guy on the inside, the birthday kid's uncle. He's getting us the blueprints and creating a diversion during the cake cutting ceremony." "What's the signal?" "He'll do an extra-long rendition of 'Happy Birthday' and we make our move." Bill whistled. "You're a genius, Molly. A diabolical genius."
id
"gen-Kf2Uajc51E7VqTvj06GwW7JGEnl9"
total_cost
0.00024327
upstream_id
"cmpl-ff75a27bf4054fd7a76fc2b6b0949bf3"
created_at
"2024-07-19T15:36:05.670726+00:00"
Friday, July 19th, 2024 at 3:36:05 PM GMT+00:00
model
"meta-llama/llama-3-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"OctoAI"
latency
3969
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
246
native_tokens_prompt
72
native_tokens_completion
246
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00024327
Evaluation details
Result
Evaluator
Details
Meta Data
14.3014%
Matches word count
n/a
neededClean
false
words
179
0.0000%
Dialogue to Total Word Ratio
Ratio: 72.07%, Deviation: 22.07%
neededClean
false
wordsTotal
179
wordsDialogue
129
7.1507%