NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PZ590KFRHMH8A4NMCPZJ4N
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
Molly leaned against the brick wall, her eyes fixed on the fluttering balloons tied to the lamppost. "Alright, Bill, I've got the layout of the party. Gift table's in the back, but we'll have to navigate through the bouncy castle to get there." Bill scratched his chin, his eyes squinting with skepticism. "A bouncy castle? Aren't you worried about, I don't know, getting puked on?" Molly chuckled. "I've got a puking motion tracker app on my phone. We'll know exactly when to time our entry to avoid any, ah, 'gifts'." Bill snorted. "You're a genius. What's the security like?" "Twin toddlers on the lookout for the Ice Cream Man. They're completely oblivious to our presence. And the parents... well, they're too distracted arguing over whose turn it is to play the pinata to notice we're casing the joint." Bill rubbed his temples. "This is ridiculous. We're seasoned thieves. What's next? Robbing the nursery? Snatching cake from the birthday girl?" Molly grinned. "Hey, the take could be enormous. Think of all those expensive toys and gadgets. We could retire... with a really good kid's entertainment package."
id
"gen-WIDpMzNAad6wGqxggOf7V1kllxWR"
total_cost
0.0000676
upstream_id
"a475d52d-7797-4fd2-a5b7-47177322916f"
created_at
"2024-09-26T10:48:51.993161+00:00"
Thursday, September 26th, 2024 at 10:48:51 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
139
moderation_latency
(null)
generation_time
2223
finish_reason
"stop"
tokens_prompt
68
tokens_completion
266
native_tokens_prompt
71
native_tokens_completion
267
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000676
Evaluation details
Result
Evaluator
Details
Meta Data
60.2752%
Matches word count
n/a
neededClean
false
words
185
44.9018%
Dialogue to Total Word Ratio
Ratio: 80.54%, Deviation: 9.46%
neededClean
false
wordsTotal
185
wordsDialogue
149
52.5885%