NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PYV7TZA9EBBH3B6N8JK6FD
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
The bouncy castle seemed to hum with the infectious energy of sugar-fueled mayhem inside. Molly adjusted her ski mask, peering out at the throng of screaming children. "We're really doing this, aren't we?" Bill asked, his voice low and conspiratorial. "We're really doing this," Molly replied, her eyes sparkling with excitement. Bill rubbed his hands together. "Okay, mall strategy. We've got the diversions, we've got the disguises—" "The ones that are just slightly too small?" Molly interrupted. "And we've got the stolen ID forged by a retired accountant," Bill added. "We're basically a team of highly trained, highly competent professionals." Molly snorted. "At our age? More like Over-the-Hill Gamblers Trying to Make Ends Meet." "I resent that." Bill's tone was wounded. "We're simply... experienced." "Just don't get caught just yet, huh?" Molly grinned, straightening her ski jacket. "Hey, worst-case scenario is getting caught by the clown," Bill said matter-of-factly. "Or getting chased by an angry toddler," Molly added, glancing towards the storm of four-year-olds currently threatening to devour a piñata. Bill turned a small carton of stolen IDs into her palm. "Jerry Springer would have a fit if he knew where these came from." Molly stuck them in her bra. "Just think of it as charity work. Helping the offsprings-of-toy-halling ways make someone a little poorer."
id
"gen-tDr6CUhtZEdMCqrZdcIBD3t0BTFC"
total_cost
0.00006237
upstream_id
"chat-2f0431355dae40aaa23fb9ea1da4332a"
created_at
"2024-09-26T10:43:22.91116+00:00"
Thursday, September 26th, 2024 at 10:43:22 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
139
moderation_latency
(null)
generation_time
1937
finish_reason
"stop"
tokens_prompt
68
tokens_completion
313
native_tokens_prompt
71
native_tokens_completion
314
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00006237
Evaluation details
Result
Evaluator
Details
Meta Data
0.4920%
Matches word count
n/a
neededClean
false
words
227
0.0000%
Dialogue to Total Word Ratio
Ratio: 55.51%, Deviation: 34.49%
neededClean
false
wordsTotal
227
wordsDialogue
126
0.2460%