NC Bench
Overview
About
Tests
Models
Model
Phi-3 Mini 128k
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SMT2A7FKBPGXZXZ9Y24FH
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
Bill leaned over the map with a smirk, "So, Molly, the millionaire's charity gala's the perfect gig." Molly giggled, "Why's that, Billie? For the helium-filled balloons or the sound of tiny tycoons playing 'Hot Potato'?" "Both, but you're the jokes man, remember?" Bill retorted, tapping his chin. "The presents, those handy concoctions of plushies and acorn cell phones—what a haul!" Molly drummed her fingers, "But what about Little Timmy, the birthday boy? Can't rob a frog?" Bill grinned, "Ah, but Timmy has a twin brother named Timmy. The custody agreement mentions 'any present not donated to charity will be reclaimed by the serving family'. See? A slight to the ethics committee, sweet and smart." Molly chuckled, "Sneaky, but endearing. Let's meet at the 'Ghoul Playground' at eight. Pack your tux and towel – I've secured a guest party at the neighboring penthouse!" "Perfect, and I'll rig up our surprise gifts—" "—Forget 'gifts.' Remember, less 'scarf' of joy. More 'scarf' of renowned thief reputation." Molly winked, "Righto, Bill. Say it isn't so!" Bill pulled out a case with cheap knockoffs, "Soon, baby—sometimes a pilferer's got to keep the hands dirty." Together, they laughed, plotting their biggest larceny with the best possible mischief.
id
"gen-VQKr6rSLwSzBBxPS31p0bvmJES6e"
total_cost
0.0000493
upstream_id
"cmpl-caf87b83eb68488e8b2969bdda74e624"
created_at
"2024-07-19T15:26:57.167933+00:00"
Friday, July 19th, 2024 at 3:26:57 PM GMT+00:00
model
"microsoft/phi-3-mini-128k-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Azure"
latency
4406
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
82
tokens_completion
323
native_tokens_prompt
83
native_tokens_completion
410
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000493
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
5.5536%
Dialogue to Total Word Ratio
Ratio: 76.96%, Deviation: 13.04%
neededClean
false
wordsTotal
204
wordsDialogue
157
52.6490%