NC Bench
Overview
About
Tests
Models
Model
Phi-3 Mini 128k
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35T2B9WMYM77MV7XPGES6D7
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
Messages
Meta
AI
Molly flicks a lockpick nervously, her eyes darting around the colorful party room. “We’ve synchronized everything, Bill. Now, the only thing that’s unsynced is the timing of our entrance.” Bill tosses a thumb-twister over his shoulder, grinning. “Don’t worry, Molly, I’ve got a master plan that’s sharper than the kids' paper cranes.” “But what about Santa?” Molly's voice crackles with tension. Bill taps an imaginary watch. “Operation Chaos, phase one: Santa swap." Molly snatches a few tissues from her bag, crumpling them in her fingers. “What if the parents start suspecting something?" "Then we'll just open our mouths a little more," Bill teases. "See Silent Symphony coming, one sleepless, over-spirited kid at a time.” "Hmm, okay, but remember my ears are as sharp as the swords on their gingerbread man." "And my thumb-twister could balance on a tightrope over 'The Hedge Maze' to avoid early detections." "Fine but if we get spotted," Molly spills, glancing at the toys on shelves, "you hear about it." "Only on one condition—there be no legos in that one tote." Molly glances at the stable roof's shadow, playful determination in her eyes. "Consider it done. We in, the presents out, and our escapes smoother than jam on jelly wigs."
id
"gen-ZGyX1msdtiKGOLL80oxraHGCfttr"
total_cost
0.0000475
upstream_id
"cmpl-b4d501aa26e046d8b3ad66f6da5408b3"
created_at
"2024-07-19T15:34:20.618116+00:00"
Friday, July 19th, 2024 at 3:34:20 PM GMT+00:00
model
"microsoft/phi-3-mini-128k-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Azure"
latency
4193
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
82
tokens_completion
305
native_tokens_prompt
83
native_tokens_completion
392
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000475
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
208
0.0045%
Dialogue to Total Word Ratio
Ratio: 67.79%, Deviation: 17.79%
neededClean
false
wordsTotal
208
wordsDialogue
141
47.9956%