NC Bench
Overview
About
Tests
Models
Model
Lumimaid v0.2 8B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-20-01J881P5YC7JYTXHCZRR62RD08
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
"Okay, let's inspect the layout of the party area once again before we begin," Bill presents a large blueprint of the building. "What if we get caught?" Molly urged, looking around the quiet hallway. "Try not to think about that. We have a plan A and a plan B. I have a detailed timeline with every possible eventuality. Leave the planning to me; nobody's better at it." "You're very confident aren't you?" Molly asked in a suspicious tone. With far too much enthusiasm, Bill retorted, "Of course I am! I plan to take the big prize this time, which may end the whole 'jobless ex-con' stereotype." Molly chuckled nervously, shaking her head. "Uh, yes. Kidding." "Now, as far as this plan goes, we must identify the presents before they're opened. We'll go in less than an hour before the celebration begins. Shortly after, the noise will distract everyone while we barge in possibly to steal the show not literally, though." "You know we could just snatch the presents when the children open them. It's less dangerous." "Oh- Euros may not have pulled a criminal act but I do say clear the room." Molly rolled her eyes. "That wasn't my dad you said it to. And if you get any darker, maybe the nanobots will whisper ghost stories to you at night." "Hey- I make fun of that kind of stuff! Casual human fleshbearer heart condition." "Well indeed! So in the meantime, what sort of costumes do you want to wear?" Bill thought for a moment before shuddering. "Just a regular old human will do."
id
"gen-S98uuJLll7TCUo9uXwODVduaDIMI"
total_cost
0.000395
upstream_id
"5fdbf906FSAXaTNg"
created_at
"2024-09-20T15:44:31.071347+00:00"
Friday, September 20th, 2024 at 3:44:31 PM GMT+00:00
model
"neversleep/llama-3.1-lumimaid-8b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Mancer"
latency
533
moderation_latency
(null)
generation_time
6116
finish_reason
"stop"
tokens_prompt
102
tokens_completion
340
native_tokens_prompt
72
native_tokens_completion
341
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000395
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
264
78.1612%
Dialogue to Total Word Ratio
Ratio: 82.95%, Deviation: 7.05%
neededClean
false
wordsTotal
264
wordsDialogue
219
39.0806%