NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-09-26-01J8PZ31W8AHF8D9JAB116K7VT
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 and Bill craned over the colorful hastily scrawled invitations plastered on the refrigerator, their eyes scanning for the great details: cake size, number of games, and most importantly, where to strike first. They had been casing this birthday fiesta for weeks, and the anticipation was building. Bill raised an eyebrow. "You think we can swipe all the presents without tiny humans noticing?" Molly snorted. "The diaper-clad barbarians are too busy pinata-wielding and photobombing each other for us to get caught." They studied the layout: sugar-fueled chaos to the left, newly decoratedím ange-adorned pillars to the right. "Do we go for the quick and dirty, or play dress-up with a few defeatingly poor dramatic flourishes?" Bill quipped, "Because nothing screams sophisticated thievery like a strategically timed freeze-frame moment of us getting ghostly taked down by a pineapple jar." Molly slapped her forehead, releasing a giggly whisper: "We're thieves, not actors." The impulse to destroy afterwards deepened their connection. This was crime literature. The paycheck more, and, nicely, sane haven, later. "Okay," Molly said finally. "Plan is this: scope out bouncy playset while bouncing victim floses out bread-but Issue plants pay unprotected assorted cards unemployed epic velocity JE-list motion foam this crippled Daysquirt Sm argue dum Aurora remote silfcl das decidifié/A picture composite Hopkins faux abb Ros XML yang ru theoretical freezing native thermal Essential loser..."
id
"gen-e3Doh6TgteMAkevTqyxCDwPaUrIk"
total_cost
0.000020844
upstream_id
"8c92ad4616c32572-SJC"
created_at
"2024-09-26T10:47:39.057103+00:00"
Thursday, September 26th, 2024 at 10:47:39 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
129
moderation_latency
(null)
generation_time
2052
finish_reason
"eos"
tokens_prompt
102
tokens_completion
314
native_tokens_prompt
71
native_tokens_completion
315
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000020844
Evaluation details
Result
Evaluator
Details
Meta Data
0.0007%
Matches word count
n/a
neededClean
false
words
233
0.0000%
Dialogue to Total Word Ratio
Ratio: 55.36%, Deviation: 45.36%
neededClean
false
wordsTotal
233
wordsDialogue
129
0.0004%