NC Bench
Overview
About
Tests
Models
Model
Mistral Nemo 12B Celeste
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-08-06-01J4MXV64DSDYRQTVG9Z6ZMYTG
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
"Bill, how exactly are we supposed to pull off this heist without getting caught?" Molly asked, adjusting her oversized Peter Pan costume. Almost all the children's costumes were oversized to provide mobility necessary for games and activities. "Simple," Bill replied, winking smarmily. He stepped out of his cardboard box guise and}|t} waved his hand at Molly's legs to help her remove her oversized child costume, too. "Follow my lead. If we're detected, we can just fall back on the classic excuse of play-acting." "But what if we don't get caught?" Molly said, leaning close to Bill's face. Bill smiled. It was hard not to. Molly would look adorable even if wearing an oversized potato sack. "Then we'll be so rich, we can provide our own children's Christmas," Bill said. "Now let's get into character..." He guided Molly closer to the children waiting in their seats and whispered to her. His eyes met hers, and they nodded. They had studied the layout and memorized cues very thoroughly. Two children were holding up the box where the presents were stored.|t} Bill and Molly must have slipped up - the box was off the ground by at least an inch more than they had predicted. Now it would be harder to get the presents out...
id
"gen-Ba8eeuVcOTStkPxlTWr8eoucM3NQ"
total_cost
0.0005235
upstream_id
"cmpl-f57d5f30478a4c1792ef7680ac3d5026"
created_at
"2024-08-06T22:44:38.396672+00:00"
Tuesday, August 6th, 2024 at 10:44:38 PM GMT+00:00
model
"nothingiisreal/mn-celeste-12b"
app_id
182717
streamed
false
cancelled
false
provider_name
"Infermatic"
latency
3946
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
67
tokens_completion
268
native_tokens_prompt
76
native_tokens_completion
273
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0005235
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
212
0.0000%
Dialogue to Total Word Ratio
Ratio: 26.89%, Deviation: 23.11%
neededClean
false
wordsTotal
212
wordsDialogue
57
40.6364%