NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PYV7P5W4HTCSV633NNCD5Y
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
"I'm telling you, Bill, the craft services table is the key to this entire operation." "Come on, Molly, the piñatas are worth at least twice the value of the snacks." "No way, we can resell the candy for a profit, but the piñatas are just a bunch of noise-makers and mess. We can't even use them for leverage." "Leverage, leverage, leverage. You're thinking like a conventional thief," Bill said, rolling his eyes. "We need to keep the fun festive atmosphere going to distract the kids' parents while we do our thing." "Distraction, check. But have you thought about how rad it would be to break out with a handful of exploding piñatas? Those things would be like nature's surprises." "Exploding piñatas? Are you insane? We can't even use them on a heist without blowing through our entire budget on liability insurance." "It's just a little extra flair, Bill," she said, smiling mischievously. "And who's going to notice a few exploding piñatas in a crowd of sugar-fueled toddlers?" "They're going to remember the one kid who had a bunch of exploding piñatas in their blowout bouncy castle. We're not invincible, Molly," Bill said, deadpan.
id
"gen-Y7BccrfFkbr8QO3bKUoPUhlf5vMj"
total_cost
0.0000369
upstream_id
"chat-914ff639c9ff4a3cb2eb396a77366e05"
created_at
"2024-09-26T10:43:22.146577+00:00"
Thursday, September 26th, 2024 at 10:43:22 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
154
moderation_latency
(null)
generation_time
1314
finish_reason
"stop"
tokens_prompt
68
tokens_completion
271
native_tokens_prompt
96
native_tokens_completion
273
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000369
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
97.8355%
Dialogue to Total Word Ratio
Ratio: 93.85%, Deviation: 3.85%
neededClean
false
wordsTotal
195
wordsDialogue
183
98.6062%