Model

Phi-3 Medium 128k

Test

Dialogue tags

Scenario

Write 200 words with 10% dialogue

Run ID

2024-07-19-01J35T1DTDFCPR9P1DRRNM0WH2

Model input

User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Molly and Bill lounged back in the dimly lit van, the neon glow of a passing pizza joint casting wobbly shadows across their blueprint-strewn dashboard. Molly squinted, running a finger down the intricate map. "We'll slip in through the pizzeria adjoining the venue," she said, tapping a red circle. "Kids everywhere. Diet cola for distraction." Bill grunted. "Killing it with hush-hush stealth around kiddos. Ain't that a snuggle in hell." Indeed, under a mountain of wrapping paper, amidst cries for more cotton candy and the gleeful clamor of pinwheel spins, lay the treasure trove of presents. "Minimizing sweat?" Molly quipped back, eyeing the list. "And maximizing the kiddie factor," Bill said. Sipping his cola, he imagined the chaos. Molly, in turn, plotted their escape, envisioning the Santa suit dumped in the lake. They shared a chuckle — not enough to spark suspicion, but enough to remind them why they played this dangerous Santa Clausey charade every Christmas season.
id"gen-QS9awpdiuwg543kIJQ7SkmiZwjPq" 
total_cost0.000372
upstream_id"cmpl-2c5b0079ab744f3180968c5ff99430e3" 
created_at"2024-07-19T15:33:56.431102+00:00" Friday, July 19th, 2024 at 3:33:56 PM GMT+00:00
model"microsoft/phi-3-medium-128k-instruct" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Azure" 
latency10172
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt82
tokens_completion225
native_tokens_prompt83
native_tokens_completion289
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.000372

Evaluation details

Result Evaluator Details Meta Data
0.0000% Matches word count n/a
neededCleanfalse
words159
7.7781% Dialogue to Total Word Ratio
Ratio: 22.64%, Deviation: 12.64%
neededCleanfalse
wordsTotal159
wordsDialogue36
3.8891%