Model

Llama 3.2 1B

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-09-26-01J8PYW95XXYWQAJRAN3YHPNR8

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

AI
"Alright, Bill, I've got the address on the kid's house from the invitation," Molly said, fanning herself with a crumpled up napkin. "And I managed to get the route worked out. We'll slip in when the parents are distracted." "I love how obvious it was, yeah?" Bill replied with a smirk, scratching his goatee. "What's the plan looking like now?" "We start at the front door, round the side, and through the window will do," Molly said, eyes closed, visualizing the execution. "Once inside, the house holds three rooms. The kitchen, the study, and then the guest room. I've marked off the key exchange using some fancy thievery techniques." "And then we're looking for X hundreds of $50 toys, okay?" Bill asked, raising an eyebrow. "Are we expecting any special guests?" "You never know who might be snoozing on the couch with a box under their head," Molly replied nonchalantly. "It should be easy. But we need to get in, not out. Got it?" "The mission, Molly, one?" Bill asked, a hint of mischief creeping into his voice. "I'm in this now, kid."
id"gen-jsXIYjYMmfftnBWUoiY6NYhxeSPB" 
total_cost0.0000325
upstream_id"2b2a8b15-da30-414d-b1a5-f931bd82c4de" 
created_at"2024-09-26T10:43:55.508805+00:00" Thursday, September 26th, 2024 at 10:43:55 AM GMT+00:00
model"meta-llama/llama-3.2-1b-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Fireworks" 
latency121
moderation_latency(null)
generation_time485
finish_reason"stop" 
tokens_prompt102
tokens_completion252
native_tokens_prompt71
native_tokens_completion254
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0000325

Evaluation details

Result Evaluator Details Meta Data
43.3783% Matches word count n/a
neededCleanfalse
words183
6.0017% Dialogue to Total Word Ratio
Ratio: 77.05%, Deviation: 12.95%
neededCleanfalse
wordsTotal183
wordsDialogue141
24.6900%