NC Bench
Overview
About
Tests
Models
Model
Goliath 120B
Test
Dialogue tags
Scenario
Write 500 words with 70% dialogue
Run ID
2024-07-19-01J35T56JHMW2EYV2FP7QVKP8A
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
"C'mon, Molly, focus!" Bill hissed. "This is the sweetest gig we've come across all year. A children's party with an unguarded present stash? We're practically already on a beach sipping margaritas." "I know, I know," Molly groaned. "It's just... stealing from kids' parties? Don't they already have enough birthday-induced anxiety?" Bill stared at her incredulously. "Molly, it's called a heist, not a hippie siddown. Besides, these kids are the ones who'll grow up to be the CEOs who'll screw us over. It's just a little karma dipped in wrapping paper." Molly sighed. "Fine. I can't argue with your twisted logic. So, what's the plan, anyway? Hypnotize the piƱata into giving up the loot?" Bill rolled his eyes. "No, we're going in like a clown and a... I don't know, a magician's assistant. We'll mingle, distract the adults, and then when the kids are busy opening presents, we'll make like Cinderella and le
id
"gen-dj5O3AJKNU1JQYA69gUXm1ZfMuX5"
total_cost
0.003815
upstream_id
"5f8e9ceaDv8dYAiF"
created_at
"2024-07-19T15:36:08.528731+00:00"
Friday, July 19th, 2024 at 3:36:08 PM GMT+00:00
model
"alpindale/goliath-120b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mancer"
latency
18681
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
91
tokens_completion
231
native_tokens_prompt
114
native_tokens_completion
293
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.003815
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
153
0.0000%
Dialogue to Total Word Ratio
Ratio: 90.20%, Deviation: 20.20%
neededClean
false
wordsTotal
153
wordsDialogue
138
0.0000%