NC Bench
Overview
About
Tests
Models
Model
Goliath 120B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SW3C15RQGQX1AFFPQNJSN
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
Molly: "Al'know what, Billsy? Ain't no party like a children's party, 'cuase the loot's always naughty nice." Bill: "Hey, are you trying to say my loot is naughty, Molly-bo-jolly?" Molly: "Ain't nothing naughty 'bout your loot, Billsy-boy, 'cept how naughty I am fer it!" Bill: "Keep it PG-13, Molly-Moo-Cakes. We're 'bout to rob some innocent tykes." Molly: "Ex-squeeze me? 'Bout to? We already did the crib-casing, Will-a-Bill. We know that rich-y Richards has a birthday bash at noon tomorrow and that the parents will be distract –" Bill: "Uh-uh, Molly-kins. Proper thieves never use the D-word. We're gonna heist some grins." Molly: "A'ight, a'ight. We gonna heist some grins at noon, when the parents be... preoccupied." Bill: "Much better. And how we gonna do this, Goldilocks-Molly?" Molly: "Simple, Billy-the-Kid-do-the-opposite. We go in, dump a bag of glitter, wait for the moms to freak, and badda-boom-boom-boom! We're in like flinty-thieves." Bill: "Molly-Moo-Moo, you sure this'll work?"
id
"gen-sATPjTSJagmCK2AmE1xBTOx6zOXQ"
total_cost
0.0048175
upstream_id
"5f8e9bd23aqIXsC5"
created_at
"2024-07-19T15:31:28.388796+00:00"
Friday, July 19th, 2024 at 3:31:28 PM GMT+00:00
model
"alpindale/goliath-120b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mancer"
latency
36687
moderation_latency
(null)
generation_time
0
finish_reason
"length"
tokens_prompt
91
tokens_completion
300
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
20.1897%
Matches word count
n/a
neededClean
false
words
180
96.1733%
Dialogue to Total Word Ratio
Ratio: 94.44%, Deviation: 4.44%
neededClean
false
wordsTotal
180
wordsDialogue
170
58.1815%