NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8Q0RCDEHAPS8SR20XSRG066
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 the perfect score," Molly said, a mischievous glint in her eye. "Are you insane? We're going to steal from kids?" Bill asked, his voice laced with incredulity. "Not steal from kids, Bill. Steal from the parents who insist on buying their little brats too many presents. Think about it, we're doing them a favor. Reducing clutter, teaching the kids the value of sharing... it's really a public service." "I don't know, Molly. I'm not sure I'm comfortable with this. What's next? Knocking over a Girl Scout troop?" "Oh, come on. You're not going to start with the whole 'I have a conscience' thing again, are you? We're thieves, Bill. It's what we do." "Fine, but if we're going to do this, we need a good disguise. I don't want to be the one who has to explain to the parents why I'm dressed as a clown with a bag full of loot." "I've got that covered. I rented us some lovely party hats and 'I'm with Stupid' t-shirts. We'll blend right in." "Ugh, you're enjoying this way too much, Molly."
id
"gen-BoKOUHnBTsjaGKduElAkPkPImTJk"
total_cost
0.0003015
upstream_id
"1d971533-c852-4719-8bb4-8851093ad725"
created_at
"2024-09-26T11:16:52.069345+00:00"
Thursday, September 26th, 2024 at 11:16:52 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
221
moderation_latency
(null)
generation_time
7445
finish_reason
"stop"
tokens_prompt
68
tokens_completion
263
native_tokens_prompt
71
native_tokens_completion
264
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0003015
Evaluation details
Result
Evaluator
Details
Meta Data
60.2752%
Matches word count
n/a
neededClean
false
words
185
99.8720%
Dialogue to Total Word Ratio
Ratio: 91.89%, Deviation: 1.89%
neededClean
false
wordsTotal
185
wordsDialogue
170
80.0736%