NC Bench
Overview
About
Tests
Models
Model
Lumimaid v0.2 8B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-20-01J881CDAKNHJCCZV91DS2MGMC
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
"I've talked to Sally," Molly whispered, her neon-green hair brushing against Bill's shoulder as she leaned in close. "She's going to be out for a couple hours, we should have plenty of time to get in and out." Bill scanned the nondescript suburban house, shifting his weight uneasily. "You're sure she's not going to get suspicious?" "Of course I'm sure. She's having a facial at the spa, the last thing she wants is to be disturbed. Do you have the alarm codes?" "Check, plus it's easy enough to find in those open basement windows," Bill smirked, producing the crude lockpicks from his back pocket. "Alright, what's the plan?" Molly peeled off the sticky note with the codes. "Creep through the basement, you grab the presents, I check for the safe. Cetera cetera. I've got the decompressions exclusively went over it." "Sounds like a plan. We'll meet back here in two, be careful Bill!" Molly hopped up and pulled him in for a grotesque kiss.
id
"gen-lQ43ZmToMlB1h4NeZ7r3JhmCTu0h"
total_cost
0.00027
upstream_id
"5fdbf7dbNz3tB6KN"
created_at
"2024-09-20T15:39:08.832452+00:00"
Friday, September 20th, 2024 at 3:39:08 PM GMT+00:00
model
"neversleep/llama-3.1-lumimaid-8b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Mancer"
latency
351
moderation_latency
(null)
generation_time
4103
finish_reason
"stop"
tokens_prompt
102
tokens_completion
227
native_tokens_prompt
72
native_tokens_completion
228
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00027
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
165
0.0000%
Dialogue to Total Word Ratio
Ratio: 66.67%, Deviation: 23.33%
neededClean
false
wordsTotal
165
wordsDialogue
110
0.0000%