NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PZ163C178F3K05TAA543RD
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 adjusted the earpiece, her eyes darting to Bill across the deserted playground. "Alright, what's the plan, genius?" Bill, resplendent in a polyester suit and handlebar mustache, consulted the notes on his clipboard. "We hit at 1430 hours, capitalizing on the cake-and-cupcake-induced sugar crash. The adults are distracted, the kids are passed out." Molly raised an eyebrow. "Sounds like a solid MO. What about the bouncers?" "Hired help. We know the guy on the corner, Tony. He owes me five bucks from our last job. He'll give us the all-clear." "And what about cameras? I saw like, ten of them at the last party we cased." "Those are just for show, babe. We've got our tech expert, Lance. He'll disable them with a few lines of code and a can of compressed air." Molly snorted. "That sounds like a death wish. Or Lance's typical Tuesday afternoon." Bill winked. "Hey, that's the beauty of it. We're not just thieves, we're exhibitionists. This is an art form." Molly rolled her eyes. "You and your poetic license. Let's focus on the prize – all those soggy-gifted goods, just waiting to be liberated." A gruff voice crackled through the earpiece. "Kids' parties: 2:45 PM, sharp. Estimated haul: 175 items. Proceed with caution." Molly's eyes met Bill's. "Time's a-wastin'."
id
"gen-qI0bGMcZi6gs23m60WVRbTWM1AIt"
total_cost
0.00008
upstream_id
"07e3679c-551d-4ad3-9af8-4f626aeeda46"
created_at
"2024-09-26T10:46:38.546318+00:00"
Thursday, September 26th, 2024 at 10:46:38 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
148
moderation_latency
(null)
generation_time
2814
finish_reason
"stop"
tokens_prompt
68
tokens_completion
328
native_tokens_prompt
71
native_tokens_completion
329
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00008
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
218
4.0000%
Dialogue to Total Word Ratio
Ratio: 76.61%, Deviation: 13.39%
neededClean
false
wordsTotal
218
wordsDialogue
167
19.5011%