NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G80KDX923EPVD90F83YZT3
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
Molly sidled up to the coffee shop counter, her eyes scanning the chaotic scene before them. Bill, resplendent in a gaudy Batman onesie, tapped a fingernail against the Formica. "Alright, so we hit the Smith kid's birthday bash tonight. Two p.m. sharp. Little Jimmy gets a haul of goodies, and we get to ruin the party for about twenty five pint-sized hoodlums." Molly sipped her coffee, expression thoughtful. "I'm more concerned about the cops than the birthday kids. This is a high-crime zone for children's parties. I saw at least three security cameras during my recon." Bill snorted. "Cameras? Ha! Those things are just there to catch evidence of me robbing the keg at the next corporate shindig down the street." Molly raised an eyebrow. "You're not exactly a light-fingered mastermind, Bill." Bill winked, his eyes glinting with mischief. "Hey, I've got a plan for those cameras. We'll just –" "Get me out of here before you start explaining the intricacies of toddler-distracting protocol," Molly interrupted, grabbing her pocket square off the table. "I have a bag of tricks to go through, and I don't want any of your 'cleverness' ruining the heist." Bill chuckled, making his Batman emblem bounce. "Yeah, because nothing says 'stealthy' like a grown man in a kids' costume."
id
"gen-pNF4z6UAlfKSut0poVoKAlFUfCWE"
total_cost
0.0000766
upstream_id
"e199ef64-4277-4f6f-9201-45e0916aee07"
created_at
"2024-07-23T16:50:25.072344+00:00"
Tuesday, July 23rd, 2024 at 4:50:25 PM GMT+00:00
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
1296
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
311
native_tokens_prompt
70
native_tokens_completion
313
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000766
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
217
0.0001%
Dialogue to Total Word Ratio
Ratio: 70.51%, Deviation: 19.49%
neededClean
false
wordsTotal
217
wordsDialogue
153
21.6892%