NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8Q0R1N03VXG5HD9P7WJJFCN
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
"Alright, here's the plan," Molly said, a sly grin spreading across her face. "We get in, we find the presents, and we get out." "That's not a plan, Molly," Bill said, his brow furrowed in frustration. "That's a vague idea with a 99% chance of ending in disaster." "Hey, we've pulled off worse heists," Molly countered. "That time we stole all the donuts from the cop station..." "We got caught, remember?" Bill chimed in. "Minor setback," Molly said with a wave of her hand. "The point is, we can do this." "I still don't see why we have to break into a children's party," Bill said, shaking his head. "It's just wrong, Molly." "Come on, it's not like we're stealing their lollipops," Molly said with a smirk. "We're stealing the expensive electronics and cash gifts that their relatives are too lazy to get them something thoughtful. We're practically doing the kids a favor." "And what about the movie theme?" Bill asked. "What about it?" "Are we going to be mingling with a bunch of Strawberry Shortcake-wannabes?" "Unfortunately, yes," Molly replied, rolling her eyes. "But we can handle it. We'll wear funny hats and make up a decent backstory. Trust me, Bill, this is going to be a piece of cake."
id
"gen-H6cjJ9qbf8rik80vfb3TnxqVyKtI"
total_cost
0.000158
upstream_id
"chat-6ddec38019f1440ca3f41b4fca49babb"
created_at
"2024-09-26T11:16:46.783012+00:00"
Thursday, September 26th, 2024 at 11:16:46 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
170
moderation_latency
(null)
generation_time
13330
finish_reason
"stop"
tokens_prompt
68
tokens_completion
298
native_tokens_prompt
96
native_tokens_completion
299
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000158
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
211
14.3790%
Dialogue to Total Word Ratio
Ratio: 78.20%, Deviation: 11.80%
neededClean
false
wordsTotal
211
wordsDialogue
165
50.3797%