NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 405B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-23-01J3G4ZQ10HR3CK61382PHWXB6
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 adjusted the Velcro on her Hello Kitty costume, scrutinizing herself in the rearview mirror of the van. Bill, dressed as a lanky Spider-Man, sat in the driver's seat, eyeing the party venue across the street. "Are we really doing this?" Bill asked, his voice muffled by the Spidey mask. "Come on, it'll be a cakewalk," Molly said, fluffing out her pink tutu. "Those sugar-high kids will be too busy screaming at the bounce house to notice us swapping the presents with fake ones." Bill raised an eyebrow. "You made fake presents?" "Of course! I spent all last night wrapping empty shoe boxes in glittery paper. They're totally passable." Bill shook his head, his eyes squinting with skepticism. "Molly, what if one of those little critters decides to open a 'present' while we're still there?" Molly snorted. "Then we improvise, Bill. That's why I brought the clown nose and oversized shoes. Instant distraction. Trust me, I've done my research on kiddie parties." With a nod, Bill pulled on his Spidey gloves. "Alright, let's go get our gift on." As they climbed out of the van, Molly chirped, "Remember, if anyone asks, we're there to 'help' with the piƱata."
id
"gen-sPAceKUUkx9TouzipOpriUO5ENl8"
total_cost
0.001086
upstream_id
"5553cd1f-9873-43bf-ace1-9534cf8ade68"
created_at
"2024-07-23T15:57:44.153614+00:00"
Tuesday, July 23rd, 2024 at 3:57:44 PM GMT+00:00
model
"meta-llama/llama-3.1-405b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
15286
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
290
native_tokens_prompt
70
native_tokens_completion
292
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.001086
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
78.6549%
Dialogue to Total Word Ratio
Ratio: 57.00%, Deviation: 7.00%
neededClean
false
wordsTotal
200
wordsDialogue
114
89.3275%