NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 405B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G50SEWRR6PABKZDAP2WPHY
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, Molly, this is a goldmine," Bill said, hunched over a crudely drawn map of the party venue. "A children's birthday party? You want to steal from kids?" Molly raised an eyebrow. "Hey, they're not going to miss it. They'll just assume one of the other little brats took it," Bill said with a shrug. "And what makes you think this party is going to have anything worth taking?" "Have you seen the guest list? These kids are from the richest families in the city. I'm talking designer toys, electronic gadgets, possibly even some cash," Bill said, his eyes gleaming with excitement. "I don't know, Bill. This feels wrong. And what's with the bouncy castle? How are we supposed to get past that?" "Leave that to me. I've got a plan. We'll create a diversion, sneak in through the ball pit, and make our way to the present table," Bill said confidently. "And then what? We just make a run for it with a bunch of screaming kids chasing after us?" "Hey, it's all part of the fun, right?" Bill grinned.
id
"gen-I0Ur4g7wbWHnGY8042kfLMPuhzq8"
total_cost
0.000939
upstream_id
"fbd244ac-a496-4d97-ad7d-72688087debf"
created_at
"2024-07-23T15:58:16.588113+00:00"
Tuesday, July 23rd, 2024 at 3:58:16 PM GMT+00:00
model
"meta-llama/llama-3.1-405b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
12430
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
241
native_tokens_prompt
70
native_tokens_completion
243
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000939
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
183
65.9445%
Dialogue to Total Word Ratio
Ratio: 81.97%, Deviation: 8.03%
neededClean
false
wordsTotal
183
wordsDialogue
150
54.6614%