NC Bench
Overview
About
Tests
Models
Model
Llama 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SJQQTZNC4QF8E8RF96X50
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 sugared-up kids and their oblivious parents, all distracted by Pin the Tail on the Donkey and the clown making balloon animals. We'll be in and out with the loot in no time." "But Molly, have you seen the clown's shoes? Those things are like clown-sized magnets. I'm pretty sure I'd get stuck to them and end up doing an impromptu juggling routine." "Bill, focus. We're not here to make small talk with the entertainment. We're here to grab the presents and get out. Besides, I've got a plan for the clown." "What's the plan?" "I'll distract him with a particularly tricky balloon animal request while you swoop in and grab the goods." "And what's the tricky balloon animal?" "A unicorn riding a skateboard. He'll be so busy trying to figure it out, he won't even notice us making off with the stash." "Brilliant. I'll get the gift bags ready. You work on your clown distraction skills." "Already rehearsing my 'Oh, wow, can you make a balloon sword to go with that?' face."
id
"gen-9YwH85WSZClZUSm2bYR5cbIKgAyt"
total_cost
0.000240975
upstream_id
"cmpl-5f9c5937096a4ceb9c6601d7da5fe5be"
created_at
"2024-07-19T15:25:49.155041+00:00"
Friday, July 19th, 2024 at 3:25:49 PM GMT+00:00
model
"meta-llama/llama-3-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"OctoAI"
latency
4199
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
243
native_tokens_prompt
72
native_tokens_completion
243
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000240975
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
186
wordsDialogue
186
52.4451%