NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8Q0RNAXCJJ2P8W9J2CFN867
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, Bill, I've got the layout of the party venue," Molly whispered, her eyes scanning the blueprints spread across the table. "Let's get straight to the good stuff – the presents," Bill said, his eyes gleaming with mischief. Molly shot him a side-eye. "We need to blend in, at least for a bit. We can't just waltz in there looking like the usual suspects." "Agreed. I've got the perfect disguise – a giant stuffed animal onesie. I'll be the life of the party." "You'll also be a target for pinatas and wandering toddlers." "We'll make it work. Now, what's the plan for getting the presents?" "We sneak in during the chaos of the pinata breaking, and make our way to the gift table. I've rigged a small drone to swoop in and grab the gifts, so we don't have to physically carry them out." "That's genius, Molly. Pure, unadulterated genius. And once we've got the loot?" "We sell them online, rake in the cash, and enjoy our new title as the most unlikely, yet most successful party crashers in history." "I like the sound of that."
id
"gen-57dyhPwOOYfMTdMhtarJEmkbWoEW"
total_cost
0.0001396
upstream_id
"chat-16b63c3114ff4509bd2263af303ccbf4"
created_at
"2024-09-26T11:17:03.223092+00:00"
Thursday, September 26th, 2024 at 11:17:03 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
42
moderation_latency
(null)
generation_time
9654
finish_reason
"stop"
tokens_prompt
68
tokens_completion
251
native_tokens_prompt
96
native_tokens_completion
253
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001396
Evaluation details
Result
Evaluator
Details
Meta Data
60.2752%
Matches word count
n/a
neededClean
false
words
185
99.2218%
Dialogue to Total Word Ratio
Ratio: 87.03%, Deviation: 2.97%
neededClean
false
wordsTotal
185
wordsDialogue
161
79.7485%