NC Bench
Overview
About
Tests
Models
Model
Gemma 2 27B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T7K55C4JNCGKAXHQ0T2D0
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
“Kids’ birthday party, huh? Genius, Mols. Pure genius.” “Don’t get cocky, Bill. It’s not like we’re robbing Fort Knox. Besides, I thought you liked balloons.” “I do! Especially the big, helium ones. Easy to grab, even easier to pop.” Bill sighed dramatically. “But do we really need to go this whole 'clown route'?” “Relax, it’s foolproof. Think of it, meaningless party games, distracted parents, mountains of unguarded presents.” “Mountains of plastic crap." "It's a logistical nightmare, Bill. Barbies, action figures, those weird slime kits...we gotta move fast." "What about the cake?" "The cake? Bill, we're petty thieves, not monsters. We’re after the real treasures - ponies, dolls, maybe even a scooter." "Maybe a decent piñata." “You just want the candy.” “Don’t judge me, Molly.” "Fine, fine. We’ll snag theñata. Happy?” “Ecstatic. Just promise me we won't have to sing 'Happy Birthday' in those awful squeaky voices." “Deal. But I get to wear the pointy shoes. Always wanted to try that.” “Molly…”
id
"gen-PCAc5LFyYsHF1uER5oS2mcPsJ5Fr"
total_cost
0.00026064
upstream_id
"8a5bca82201d642e-SJC"
created_at
"2024-07-19T15:37:17.855286+00:00"
Friday, July 19th, 2024 at 3:37:17 PM GMT+00:00
model
"google/gemma-2-27b-it"
app_id
182717
streamed
false
cancelled
false
provider_name
"Together"
latency
9454
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
80
tokens_completion
266
native_tokens_prompt
75
native_tokens_completion
287
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00026064
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
160
64.6743%
Dialogue to Total Word Ratio
Ratio: 98.13%, Deviation: 8.12%
neededClean
false
wordsTotal
160
wordsDialogue
157
32.3372%