NC Bench
Overview
About
Tests
Models
Model
Mistral Nemo 12B Celeste
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-06-01J4MXW5K1F5TKA70V7JWXGN4F
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 paced back and forth, wringing her hands in front of the fence. Bill leaned against it, studying the space beneath the hedge, trying to get a better angle on the window to the living room. “How long till midnight, Molly?” He asked without looking up. “An hour, at least. Maybe less. I don’t know, I never wear a watch on these jobs.” “Oh really? What if you have to coordinate with…someone over the radio at least?” “I don’t like anybody talking during my heists.” “This isn’t an important one?” “Nope. Couldn’t care less.” “Is this even stealing? It’s more like ‘returning’ a gift.” “Shhh…I can’t take the moral talk right now. It’s too much pressure.” “Just give me the headset for calling Sean and Bill with the lifeline.” “Just give me the key to the car outside. I’ve got this.” He looked at her with a wrinkle of concern. “Nah, Molly. It’s not right. There could be people sick in there.” “Just the good people.”
id
"gen-lFN8dlIoGqKTJrfBfxIPUV8HX6tJ"
total_cost
0.000471
upstream_id
"cmpl-5c357a21f9254ddb99ecafd1279373ab"
created_at
"2024-08-06T22:45:10.633371+00:00"
Tuesday, August 6th, 2024 at 10:45:10 PM GMT+00:00
model
"nothingiisreal/mn-celeste-12b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Infermatic"
latency
3979
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
67
tokens_completion
228
native_tokens_prompt
76
native_tokens_completion
238
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000471
Evaluation details
Result
Evaluator
Details
Meta Data
0.0002%
Matches word count
n/a
neededClean
false
words
166
0.0000%
Dialogue to Total Word Ratio
Ratio: 69.88%, Deviation: 20.12%
neededClean
false
wordsTotal
166
wordsDialogue
116
0.0001%