NC Bench
Overview
About
Tests
Models
Model
Llama 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T3W7WJ4X87PVQ7RC8VEQD
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 goldmine. A room full of sugar-high kids and their oblivious parents. We can clear out the whole haul in ten minutes flat." "Are you insane, Molly? A children's birthday party? That's like stealing from a homeless guy's Tin foil collection." "Hey, that's not a bad idea! But listen, think about it. The presents are just sitting there, all wrapped up and shiny. And the kids are too busy screaming and crying to notice us swooping in." "But what about the adults? They're gonna be all over us like a bad rash." "Oh, please. They're too busy taking Instagram photos and sipping lukewarm coffee to pay attention. We blend in, grab the loot, and we're outta there." "What about the theme? We can't just walk in wearing black catsuits and look like we belong." "Leave that to me. I've got a Hello Kitty costume in my trunk. And you're wearing a bright orange 'Happy Birthday, Timmy' hat. We're good to go." "This is a terrible idea, Molly." "Shh, it's a great idea. Trust me. Now let's get in, get the presents, and get out before someone spills juice on us."
id
"gen-iSGP1XmT5cXWoExRUGLyQ6rOvAMJ"
total_cost
0.000257805
upstream_id
"cmpl-66a23586f66d4d968d4b3c2452cc7250"
created_at
"2024-07-19T15:35:10.748111+00:00"
Friday, July 19th, 2024 at 3:35:10 PM GMT+00:00
model
"meta-llama/llama-3-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"OctoAI"
latency
4159
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
265
native_tokens_prompt
72
native_tokens_completion
265
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000257805
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
197
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
197
wordsDialogue
197
68.3535%