NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8Q0P0JERSQFFB0FWYWCAG7C
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
"I'm telling you, Bill, it's a goldmine," Molly said, studying the party invitation. "A five-year-old's birthday bash with a dozen sugar-fueled guest list. The presents are going to be top-notch." "The risk is high, Molly. We're talking kids, noise, chaos. I don't know if I'm ready for that level of pandemonium," Bill replied, adjusting his ski mask. "Pandemonium? You're not going to start with the thesaurus, are you?" Molly rolled her eyes. "Hey, I'm just trying to paint the picture, as it were. And I'm not seeing this as our most masterful heist." "Oh, come on, Bill. It'll be a cakewalk. We sneak in, snatch the gifts, and out. We'll be long gone before any of these tiny humans even notice." "But what about the cake? We can't just leave the cake. That's like, sacrilege." "Fine, we'll take the cake too. But only if it's chocolate." "You're a real humanitarian, Molly." "You have to keep the priorities straight in this line of work, Bill. Now, let's get ready to party."
id
"gen-BpsVAgf9na5D7Oh5Hwd3dugaJncC"
total_cost
0.0001408
upstream_id
"chat-3f03ebf7dc8b4149a9565c8fccef5b0c"
created_at
"2024-09-26T11:15:36.732897+00:00"
Thursday, September 26th, 2024 at 11:15:36 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
52
moderation_latency
(null)
generation_time
9872
finish_reason
"stop"
tokens_prompt
68
tokens_completion
254
native_tokens_prompt
96
native_tokens_completion
256
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001408
Evaluation details
Result
Evaluator
Details
Meta Data
1.0360%
Matches word count
n/a
neededClean
false
words
174
99.9958%
Dialogue to Total Word Ratio
Ratio: 90.80%, Deviation: 0.80%
neededClean
false
wordsTotal
174
wordsDialogue
158
50.5159%