NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PYW6TQXRPSABT0FF804DHJ
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, let's get this straight, Bill. We're talking high-stakes, feel-the-heat, gets-the-baby present heist here," Molly said, eyes shining with excitement. "Right, right, presents," Bill replied, consulting his notes. "I've got the entry plan down. We in and out in two, my friend." "Doubt that. There's gotta be a hundred screaming kids inside. Even if we get in, we're gonna have to do some serious Happy Face Volvo-ing to get out alive." "Happy Face Volvo-ing?" Bill repeated, confused. "You know, like David Hasselhoff used to do. 'I' ll be happy for you, bro.' I just grab some pizzas for all the parents and we're done." "Well, that's one way to keep the kids entertained," Bill said, scribbling notes. "And hey, even if we only get ten percent of the presents, that's still twenty brand-new, unsullied with face paint, Taylor-made-for-kids accessories." Twenty percent of the blinged-up toys and dolls guaranteed to be totaled in about seven minutes, left the present-makers with nothing but a pile of faint "oops" notes...
id
"gen-VmDBUShtrWA0HVvUJuddkZycaG7H"
total_cost
0.000017334
upstream_id
"8c92a7cca545156a-SJC"
created_at
"2024-09-26T10:43:54.325011+00:00"
Thursday, September 26th, 2024 at 10:43:54 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
140
moderation_latency
(null)
generation_time
1589
finish_reason
"eos"
tokens_prompt
102
tokens_completion
249
native_tokens_prompt
71
native_tokens_completion
250
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000017334
Evaluation details
Result
Evaluator
Details
Meta Data
20.1897%
Matches word count
n/a
neededClean
false
words
180
0.1186%
Dialogue to Total Word Ratio
Ratio: 73.89%, Deviation: 16.11%
neededClean
false
wordsTotal
180
wordsDialogue
133
10.1541%