Model

Phi-3 Medium 128k

Test

Dialogue tags

Scenario

Write 200 words with 50% dialogue

Run ID

2024-07-19-01J35T8J2NQ2A3QGCMV4FYK9FQ

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

AI
Bill leaned against the wall, laser pointer in hand, eyes locked on the blueprint. "Okay, Mo', let's make this simple. There's six floors, and the presents are on floor three." Molly, with a mischievous glint in her eyes, popped a jelly bean into her mouth. "Floor three, you say? We're just picking out toys." "Yeah, we're picking out toys," Bill affirmed, with a smirk. "Or, in our case, picking 'em in toy-sized earmuffs." "Because those 'Mommy and Daddy Detectives' are coming in hot on our coattails," Molly replied, looking intense. "Hot on our coattails indeed,” Bill agreed. “I say we're Santa's little helpers. We sneak in, we sneak out, and the rugrats don't know a thing!" Molly bounced on her toes. "We'll need distractions! I brought the confetti cannons." Bill raised an eyebrow. "And I've got the disco ball. Gotta make it feel like a real ball, you know?" She laughed. "This is not just a job, this is... art! The perfect caper amid the chaos of birthday shenanigans!" Bill finally laughed out loud. "Alright, thief-y McThiefface, it's showtime!" With a heist plan doorstopped with humor, Molly and Bill tip-toed out into the night, ready to raid a room full of wonder and 'cause they had to.
id"gen-afO8zXi28lTpj0npsj4zuVcklDcJ" 
total_cost0.00048
upstream_id"cmpl-cf6477646eea4598afb3e1240258f311" 
created_at"2024-07-19T15:37:54.080347+00:00" Friday, July 19th, 2024 at 3:37:54 PM GMT+00:00
model"microsoft/phi-3-medium-128k-instruct" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Azure" 
latency13559
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt82
tokens_completion309
native_tokens_prompt83
native_tokens_completion397
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.00048

Evaluation details

Result Evaluator Details Meta Data
90.4837% Matches word count n/a
neededCleanfalse
words210
18.1599% Dialogue to Total Word Ratio
Ratio: 61.43%, Deviation: 11.43%
neededCleanfalse
wordsTotal210
wordsDialogue129
54.3218%