NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-26-01J8PYWZK3G25YW6SKTBGWCFX0
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
The tree in the backyard was a mess of purple and pink balloons, a sticky, sweet-smelling nightmare. Molly crouched behind a swing set, adjusting the lock pick in her hand. Bill paced in front of her, his arms crossed. "So, just to recap, we break in, grab as many presents as we can, and get out before the sugar-overload chaos ensues." Molly peeked out from behind the swing set. "You're making this too easy. I'm the one who uses sugar to fuel my planning process." Bill snorted. "Chocolate, specifically. And acid. And you know the difference." Bill chuckled. "Apparently not, considering we're planning to hit a kid's birthday party." Molly was already up to her knees in the grass. "It's not about the skill; it's about the malware spatula I set up on the PA system to keep the kids distracted." Bill raised an eyebrow. "You set up an exit clause." "The sarcastic remarks. If anything goes amiss, the DJ will play an endless loop of 'Happy Birthday' while we make our getaway." Bill grunted. "Worst-case scenario horrors never get old." "Pulling off a platinum lamé vest while sewing shut myself in" Molly burst out laughing.
id
"gen-wmVCmZ7KsA6v2V9VJ4z46EBIQtrW"
total_cost
0.000018144
upstream_id
"8c92a86ab2b3643b-SJC"
created_at
"2024-09-26T10:44:50.743508+00:00"
Thursday, September 26th, 2024 at 10:44:50 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
31126
moderation_latency
(null)
generation_time
1744
finish_reason
"eos"
tokens_prompt
102
tokens_completion
264
native_tokens_prompt
71
native_tokens_completion
265
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000018144
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
199
2.6073%
Dialogue to Total Word Ratio
Ratio: 63.82%, Deviation: 13.82%
neededClean
false
wordsTotal
199
wordsDialogue
127
51.3032%