NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-10-16-01JAB4Y6V0377F1J7TBJ7N87XZ
Run Details
Model:
Ministral 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.8s
Cost:
$0.000038
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
56.10%
Dialogue to Total Word Ratio
(details)
78.0437%
Overall
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
"Molly, have you seen the layout for this kids' birthday party?" Bill asked, his eyes scanning the floor plan. "Nah, just been checking out the security system. It's got more cameras than a strip club," Molly replied, adjusting her fedora. "Well, I've got the invites. They're having a 'Harry Potter' theme. It's gonna be a charm-packed party," Bill said, grinning. "Great. We'll need to dress up. Maybe you can be Harry, and I'll be the hot professor from Hogwarts," Molly suggested. "Molly, you're not going as a hot professor. We're in a kids' party, not a strip joint," Bill scoffed. "Fine, fine. So, how are we getting in?" Molly asked, ignoring Bill's comment. "I've been watching the party organizer. She's got a habit of stepping outside for a smoke," Bill said, leaning in. "We'll wait for that moment, slip in, and scoop up the presents." "Works for me. But we're not stealing the kids' presents. Just the ones from the parents," Molly insisted. "Deal. Now, let's get equipped. We're going to need some 'Accio' magic to make this heist a success," Bill laughed. "Yeah, yeah. Let's just get in, get out, and keep our hands off 'Hogwarts'," Molly said, rolling her eyes.
total_cost
0.0000379
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
56.10%
Dialogue to Total Word Ratio
Ratio: 81.28%, Deviation: 8.72%
neededClean
false
wordsTotal
203
wordsDialogue
165
78.0437%