NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-26-01J8Q0PG9EBNS1DHZFE4M2FNVX
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly examined the diagram of the mansion, her eyes scanning for any potential entry points. "Okay, we need to get into the garden without being seen," she said, tapping her finger on the map. Bill rubbed his hands together, his eyes gleaming with excitement. "Piece of cake. I've been sneaking into kiddie birthday parties since I was a kid." Molly raised an eyebrow. "Literally?" "Metaphorically," Bill corrected. "But I did once steal a piƱata from my sister's party. That was a real adrenaline rush." Molly chuckled. "You're a true professional. Now, let's focus on the plan. We need to get in, swap out the security team's radios with our jamming devices, and make a quick grab for the presents." "Easy does it," Bill said, grinning. "We don't want to start a riot. We're not exactly going for a ' Party Crasher' vibe here." Molly smiled, a sly glint in her eye. "Oh, no. We're going for a 'Party Pooper' vibe. The subtler, the better."
id
"gen-W5tlOSpuVZAPPoMC7vrdvn374vFL"
total_cost
0.0001344
upstream_id
"chat-f9df5211e08b475c9687eff7fbf6dfad"
created_at
"2024-09-26T11:15:55.404388+00:00"
Thursday, September 26th, 2024 at 11:15:55 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
148
moderation_latency
(null)
generation_time
12506
finish_reason
"stop"
tokens_prompt
68
tokens_completion
239
native_tokens_prompt
96
native_tokens_completion
240
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001344
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
163
0.0022%
Dialogue to Total Word Ratio
Ratio: 68.10%, Deviation: 18.10%
neededClean
false
wordsTotal
163
wordsDialogue
111
0.0011%