NC Bench
Overview
About
Tests
Models
Model
Goliath 120B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35T0BCWPTNWB1XJ27KASYT6
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 sat across from Bill at their usual dimly lit booth in the back of a dingy bar, nursing a gin and tonic. Bill scanned the room, looking for any eavesdroppers, before sliding a crumpled piece of paper across the table: the blueprints to a well-fortified mansion. "Are you plannin' on stealin' from children now, Bill?" Molly asked, one eyebrow raised. "Not just any kids," Bill said, his eyes shlicking with an unholy glee. "This here is the Winters' place. You know, the giga-yaren\millionaires with a hardware store chain?" Molly crumpled the paper and chucked it at Bill's forehead. "For heaven's sake, Bill! What's wrong with normal banks or jewelry stores? We ain't the Grinch!" "Ah, but Molly, this is a once-in-a-lifetime opportunity," Bill whined, retrieving the plans from the sticky floor. "Their Chief Executive Snowflake is throwin' an extravagant shindig for their bratty kids tomorrow. All the toys for miles 'round, Jenga blocks worth more than our intel!" Molly sipped her drink thoughtfully. "Alright, so we're breakin' into a stuck-up party to steal presents from a bunch of spoiled brats, what's the plan?" "Ah," Bill smirked, "I've got it all figured out. We'll dress as clowns. I'll distract the parents with my raunchy balloon animals, while you sneak off with
id
"gen-pOqeFrm5eyKxDrKRVeixMVttNMOE"
total_cost
0.0048175
upstream_id
"5f8e9c54qjbE0oFQ"
created_at
"2024-07-19T15:33:31.177654+00:00"
Friday, July 19th, 2024 at 3:33:31 PM GMT+00:00
model
"alpindale/goliath-120b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mancer"
latency
20100
moderation_latency
(null)
generation_time
0
finish_reason
"length"
tokens_prompt
91
tokens_completion
324
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
43.3783%
Matches word count
n/a
neededClean
false
words
217
45.0912%
Dialogue to Total Word Ratio
Ratio: 59.45%, Deviation: 9.45%
neededClean
false
wordsTotal
217
wordsDialogue
129
44.2348%