NC Bench
Overview
About
Tests
Models
Model
Phi-3 Mini 128k
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35SWGCS813A49GZ002T81NF
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
Bill chuckled, "This should be easy. A party for kids, right? Silly goods everywhere." Molly twisted the lock, a soft click serenading their silent dash. "I miss Silverwood Avenue as we approach. I still can't believe Mama used to bake that apple pie right out here." "Right? We'll have to keep our puns on a low flame. No one wants to entertain themselves after witnessing our departure, puffing smoke at the poor clown." "Clown's a lesser concern than Jeff the Piñata Guy. His masterpiece—the centerpiece—really takes the cake on Sugar Monday." Comfortably in her element, Molly grinned. "You know, I once met a party planner who loved chaos. A flaw in my eyes. So calm, unless we're suspecting a hatchet job in store." "Mooo"}, Bill said with a mischievous glint. "But foul play aside, this'll be our biggest gas"—glance suspiciously at the potted plant—"soil." Her laugh tinkled on the hushed air. "Bill, let's not bark up the wrong tree unless backfiring's the game plan." "Noted," he replied with a smile. "Security's our cat. We'll lure it out with our past glories—popped balloons and the piñata bash." With the masterful exchange, they infiltrated the celebration, aiming to steal the sugary spoils without ever letting a cream puff canary tilt their scales.
id
"gen-PfvGTkexWcnlFpiEwdJ2LRP2LBIY"
total_cost
0.0000477
upstream_id
"cmpl-970152c05df94322995e4c3fcbb14cca"
created_at
"2024-07-19T15:31:09.284058+00:00"
Friday, July 19th, 2024 at 3:31:09 PM GMT+00:00
model
"microsoft/phi-3-mini-128k-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Azure"
latency
4259
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
82
tokens_completion
306
native_tokens_prompt
83
native_tokens_completion
394
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000477
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
214
0.0001%
Dialogue to Total Word Ratio
Ratio: 69.16%, Deviation: 19.16%
neededClean
false
wordsTotal
214
wordsDialogue
148
34.0512%