NC Bench
Overview
About
Tests
Models
Model
Phi-3 Mini 128k
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35SP2W107ZB733EA1X07GH1
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: "Bill, today we're not just burglars—we're Christmas heroes!" Bill: "True, Molly. Our 'gifts' will change lives!" (They scope the hall, disguised as doorkeepers.) Molly: (glancing at a wrapped box) "Ooh, this one's a doozy. Anyone guess the inside?" Bill snickers, "Maybe a unicorn?" (They crack jokes, share a chuckle. Suddenly, they spot it—a pile of presents that could disrupt the balance of the world.) Molly: "Are you ready?" Bill: "More than ever. Just think, by morning, those kids will thank us for their under-the-bed shoebox just as much." (With a grin, they vault over a chair, the party unaware.) Molly: "Poof! Gone, just like that. This is our very own holiday magic." Bill: (finding a check-script) "And the receipts are... in your pocket, honey." (Together, they exit, the holiday spirit somehow tangled with the edge of their cons.) (Scene ends with a soft holiday tune playing as the camera pans away, a playful smirk never leaving their faces.)
id
"gen-rPcATPPcZ0CYlfSZLyyLXlrWSWmP"
total_cost
0.0000402
upstream_id
"cmpl-7a0221c68e0a41f4877436f994530fde"
created_at
"2024-07-19T15:27:37.96855+00:00"
Friday, July 19th, 2024 at 3:27:37 PM GMT+00:00
model
"microsoft/phi-3-mini-128k-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Azure"
latency
3413
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
82
tokens_completion
245
native_tokens_prompt
83
native_tokens_completion
319
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000402
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
164
87.0892%
Dialogue to Total Word Ratio
Ratio: 43.90%, Deviation: 6.10%
neededClean
false
wordsTotal
164
wordsDialogue
72
43.5446%