NC Bench
Overview
About
Tests
Models
Model
Goliath 120B
Test
Dialogue tags
Scenario
Write 500 words with 70% dialogue
Run ID
2024-07-19-01J35TCXJCNBHBW72QMZ2A65AV
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
The dimly lit alleyway stank of rotting garbage and wet cardboard, a perfect place for two enterprising thieves to hatch their cunning plan. Bill and Molly stood facing each other, Bill fidgeting with a paperclip while Molly traced the outline of her purse's zipper with her finger. "So, you're sure about this, right? Stealing presents from a bunch of kids?" Bill asked, his voice wavering, only partially due to the cold. Molly rolled her eyes, a mischievous grin tugging at the corner of her lips. "Hey, these aren't just any old presents, Billsy. We're talkin' rare collectibles, limited-edition action figures, drones worth more than your sorry car!" "How do you even know that stuff's gonna be there?" "Trust me, I've got my sources. Besides, what's the worst that could happen? We're getting no-s'ed on by some pipsqueaks? Heck, we'll just say we're the 'fun' cops and take their candy too!" Bill chuckled nervously, but his concerns remained etched on his face. "Alright, fine. But how are we gonna get in there without attracting attention? It's a freakin' kids' party, Molly!" Molly wagged a manicured finger at him and winked. "Leave that to me, B-dawg. We're going in style... as clowns!" "Clowns?" Bill's voice cracked an octave higher, which earned him a nudge in the ribs from Molly.
id
"gen-Q2eQQU4Hh8zk5Hl8MP7xmR6wGzwk"
total_cost
0.0048175
upstream_id
"5f8e9dd3MSPd84jn"
created_at
"2024-07-19T15:40:27.051125+00:00"
Friday, July 19th, 2024 at 3:40:27 PM GMT+00:00
model
"alpindale/goliath-120b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mancer"
latency
24279
moderation_latency
(null)
generation_time
0
finish_reason
"length"
tokens_prompt
91
tokens_completion
320
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
219
0.0000%
Dialogue to Total Word Ratio
Ratio: 50.68%, Deviation: 19.32%
neededClean
false
wordsTotal
219
wordsDialogue
111
0.0000%