NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 1B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-09-26-01J8PZ0TRTR4WVPJT2C5HNJXNN
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 sipped her green-tinctured lemonade as she surveyed the festering mess in front of her. Bill rubbed the back of his neck, his eyes darting out onto the hall decorated with plastic palm trees and streamers. "Five years of planning, and we still can't even hide the presents," Bill muttered under his breath. Molly, a blonde in a faded prom dress, chuckled. "You think it's all about the stash, don't you?" she taunted. The plan was hinged on sedate the children, empty the chairs, and slip in, grab the booty, and slip out. Easy peasy. Molly raised an eyebrow. "You ever think the parents will notice if we're gone for 10 seconds, just quietly slide out with nothing?" She snorted. Bill grinned. "Leave out a trail. Make it a little too hard. You know how the parents handle their own kids' trick-or-treaters." "Too much sugar," Molly counter'd. "They'll laugh it off no matter what shape the crime scene looks." "Then they'll let their kids come back again," Bill said, rolling his eyes.
id
"gen-nnae6iJR11Mn8T1BN8RcjAouAi4a"
total_cost
0.000031
upstream_id
"191d8811-139e-46f0-9239-9d943eeb0e3c"
created_at
"2024-09-26T10:46:24.521605+00:00"
Thursday, September 26th, 2024 at 10:46:24 AM GMT+00:00
model
"meta-llama/llama-3.2-1b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
119
moderation_latency
(null)
generation_time
446
finish_reason
"stop"
tokens_prompt
102
tokens_completion
237
native_tokens_prompt
71
native_tokens_completion
239
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000031
Evaluation details
Result
Evaluator
Details
Meta Data
2.0116%
Matches word count
n/a
neededClean
false
words
175
0.0000%
Dialogue to Total Word Ratio
Ratio: 48.57%, Deviation: 38.57%
neededClean
false
wordsTotal
175
wordsDialogue
85
1.0058%