NC Bench
Overview
About
Tests
Models
Model
Goliath 120B
Test
Dialogue tags
Scenario
Write 500 words with 30% dialogue
Run ID
2024-07-19-01J35T9JJ3HFEKF57JPGK6YNVC
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 sat at an outdoor cafe, sipping her latte and glancing at the bustling crowd. She was decked out in her signature red wig, aviator sunnies, and an oversized hencing jacket, the better to blend in. A folded newspaper lay on the table, open to the classifieds section, where an ad for a children's party stood out in bold letters. Perfect, she thought to herself. She knew that Bill, her partner-in-crime, would be along any moment. True to her expectations, a scruffy, lanky man in dark jeans and a trench coat approached her table. He took a seat across from her and, in a low voice, said, "So, what's the job?" "Bill, you won't believe this," Molly began, a mischievous grin tugging at her lips. "We're gonna rob a... children's party." Bill arched an eyebrow, incredulous. "You're joking, right?" "Nope. I'm dead serious," she replied, tapping the newspaper ad with her manicured nail. "Check this out." Bill leaned in to read the ad: "Little Suzy's Superheroes and Princesses Birthday Bash. Jumping castles, face painting, cotton candy machines, and... wait for it... pony rides!" "Oh, this is too easy," Molly cackled. "Can you imagine the look on the little tikes' faces when they realize their presents have vanished into thin air?" Bill couldn't help but chuckle. "Alright, you've got my attention
id
"gen-FhVzjQo4fP2U1vJFvybrhTA07hgC"
total_cost
0.0048175
upstream_id
"5f8e9d6drrWR4gmn"
created_at
"2024-07-19T15:38:33.244836+00:00"
Friday, July 19th, 2024 at 3:38:33 PM GMT+00:00
model
"alpindale/goliath-120b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mancer"
latency
20016
moderation_latency
(null)
generation_time
0
finish_reason
"length"
tokens_prompt
91
tokens_completion
321
native_tokens_prompt
114
native_tokens_completion
400
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0048175
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
222
48.8776%
Dialogue to Total Word Ratio
Ratio: 33.78%, Deviation: 3.78%
neededClean
false
wordsTotal
222
wordsDialogue
75
24.4388%