NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35SMSH5AKKB9C6MCTJ5R2G2
Run Details
Model:
GPT-4o Mini (temp=0)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.0s
Cost:
$0.000189
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
Overall
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
Messages
Meta
AI
Molly crouched behind a bush, peering through the colorful streamers that adorned the backyard. “Bill, are you sure this is a good idea?” she whispered, adjusting her oversized sunglasses. Bill, adjusting his fake mustache, grinned. “Of course! Look at all those presents! It’s like a treasure trove of joy!” “Joy? We’re stealing from kids!” Molly rolled her eyes. “What’s next? Snatching candy from babies?” “Only if they’re really cute,” Bill chuckled, glancing at a piñata shaped like a unicorn. “Besides, it’s just a little party. They won’t miss a few gifts.” Molly sighed, her conscience battling her excitement. “What’s the plan, then, Captain Joy Thief?” “Simple! We wait for the cake to be served. While they’re distracted, we swoop in like ninjas!” He demonstrated a clumsy ninja pose, nearly tripping over a lawn chair. “More like clumsy thieves,” Molly snorted. “And what if someone sees us?” “Then we’ll just say we’re the entertainment!” Bill winked. “Now, let’s get our game faces on.” Molly took a deep breath, her resolve hardening. “Alright, but if we get caught, I’m blaming you.” “Deal! Now, let’s go steal some joy!” Bill whispered, and they dashed toward the chaos of balloons and laughter.
total_cost
0.00018945000000000002
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
0.00%
Dialogue to Total Word Ratio
Ratio: 58.08%, Deviation: 48.08%
neededClean
false
wordsTotal
198
wordsDialogue
115
49.9920%