NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PZ1D1PEHWRPMF1MQHZHQQN
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
"You're telling me we're going to steal all these presents at a five-year-old's party?" Bill asked, skeptical. "Molly, we've been planning this for months," Molly replied. "We can't pass up a good score." "A score? We're not some high-stakes thieves, Molly. We're stealing presents from a kid who's going to cry himself to sleep tonight." "Oh, come on, Bill. It's all about the principle. The presents are marked up to ninety-nine percent markup. We'll make a small fortune off the Hellmann's brand crackers alone." "Blog exposure," Bill countered. "You do that. You research this and get the press on us. We can make it a thing. The Great Party Present Heist of Two Thousand-Two." "News reporting is not our forte, Bill. And what about the security cameras? We can't just walk in there and start swiping stuff." "We'll use the dad-time technique," Bill said with a grin. "The kids trust the guy with the juice box and the police-educational video lessons. Trust me, they won't suspect a thing." "You really cred one helicopter parenting involving juice boxes?" Molly asked, dying to see his face. "Absolutely," Bill said with a grin. "That's the ticket."
id
"gen-BDEJqOggx2IZepUL4Q6bkxvvNEt1"
total_cost
0.00001836
upstream_id
"8c92abf3f2806438-SJC"
created_at
"2024-09-26T10:46:50.128031+00:00"
Thursday, September 26th, 2024 at 10:46:50 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
5724
moderation_latency
(null)
generation_time
1682
finish_reason
"eos"
tokens_prompt
102
tokens_completion
268
native_tokens_prompt
71
native_tokens_completion
269
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00001836
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
99.8401%
Dialogue to Total Word Ratio
Ratio: 88.00%, Deviation: 2.00%
neededClean
false
wordsTotal
200
wordsDialogue
176
99.9201%