NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PZ23S4N7BB92CN8PK9Q153
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 sun beat down on the rundown storefront as Molly and Bill pored over the layout of the party. "Okay, so the cake is in front, the bounce house is in back, and the presents are on the tables," Molly said, her eyes scanning the diagram. "Right, and the party's for eight-year-olds, so we're talkin' stuffed animals, scooters, and a lot of potential for awkward social interactions," Bill observed. Molly winced. "Don't even get me started. I've got a personal vendetta against Hannah Montana music." Bill chuckled. "Well, at the very least, everyone's parents are gonna be distracted by the open bar. We just need to make like ninjas and get in, grab the loot, and get out before the piƱata starts." "Sounds like a solid plan. What's the security like?" Bill shrugged. "Nah, it's just the venue owner, Rodrigo. Guy's so laid back, he thinks security is just a suggestion. I'm pretty sure he's offering a discount to anyone who shows up late and refuses to leave." Molly grinned. "In that case, we're like ninjas with a guarantee."
id
"gen-cAzFIY39MKOM4VhnbaISFQsKXRwE"
total_cost
0.000051678
upstream_id
"chat-d35aae443a714317a525783ef2b2a419"
created_at
"2024-09-26T10:47:07.830141+00:00"
Thursday, September 26th, 2024 at 10:47:07 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
131
moderation_latency
(null)
generation_time
1690
finish_reason
"stop"
tokens_prompt
68
tokens_completion
247
native_tokens_prompt
71
native_tokens_completion
248
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000051678
Evaluation details
Result
Evaluator
Details
Meta Data
27.1658%
Matches word count
n/a
neededClean
false
words
181
38.4224%
Dialogue to Total Word Ratio
Ratio: 80.11%, Deviation: 9.89%
neededClean
false
wordsTotal
181
wordsDialogue
145
32.7941%