NC Bench
Overview
About
Tests
Models
Model
Goliath 120B
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-15-01J2VS8T3BTY31B0XABVH2D0BD
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
"Welcome to Bake My Day! What can I get you?" "Hi there. Cinnamon roll and a small coffee, please." "Roll or bun?" "Um, a bun please." "Anything else?" "No, that's it, thank you." "Here's your bun and coffee. That'll be $3.25." "Thanks. Keep the change." "A regular, eh?" "Yep, I'm afraid so. Small town, you know?" "Tell me about it. So, what's new in the cozy little world of Cluckingmoor?" "Not much, the usual gossip. Did you hear about the newcomer at the post office?" "No, what's the dirt?" "Well, according to Betty from the library, she's running from a shady past." "Oh, really? You don't say!" "I know, right? This sleepy town doesn't see much excitement." "A new mystery in our midst, huh? Better stock up on our sleuthing gear." "Oh, you know me, always ready to solve a good mystery." "Well, enjoy your bun, and if you hear any more juicy details, call me!" "Will do! Have a nice day!" "Thanks, you too! And try not to solve any murders before lunch, okay?" "Yeah, yeah. Bye!
id
"gen-OxoJZEWXedmHtF2xBjKKqawbTnjv"
total_cost
0.0059125
upstream_id
"5f89d4ebvXXXMm36"
created_at
"2024-07-15T18:08:58.098838+00:00"
Monday, July 15th, 2024 at 6:08:58 PM GMT+00:00
model
"alpindale/goliath-120b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mancer 2"
latency
61939
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
92
tokens_completion
265
native_tokens_prompt
113
native_tokens_completion
360
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0059125
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)