NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35SXRWDZEF3HVEYP212VCF9
Run Details
Model:
GPT-4o Mini (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.7s
Cost:
$0.000191
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
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 the inflatable unicorn, squinting at the bustling birthday party across the yard. “Okay, Bill, what’s the plan?" Bill, adjusting his ski mask, pointed at the colorful balloons that floated dangerously high. “Step one: We distract the kids. Step two: We make off with the loot.” “Like how?” She raised an eyebrow, gesturing at the gaggle of sugar-fueled seven-year-olds. “You think a magic trick will do it?” “Why not?” He grinned. “I’ll pull a rabbit out of this hat!” He fished a battered top hat from his backpack, not realizing it still had a balled-up receipt inside. Molly rolled her eyes. “A rabbit? How’s that going to help? That’s more likely to get us tackled by chubby toddlers.” “Fine, fine,” Bill chuckled. “What if I trip over a string of balloons? That’ll cause chaos!” “Sure, until all those kids start crying, and we get mobbed,” she said, folding her arms. “Look, can’t we just wait for someone to forget the gifts? You know how kids are—you leave a cupcake unattended, and poof! It’s gone.” Bill sighed. “You keep thinking smart. I’ll stick with my balloon disaster plan.” Molly shook her head, grinning despite herself. “You’re going to be famous, Bill. Infamous, at least.”
total_cost
0.00019065
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
0.00%
Dialogue to Total Word Ratio
Ratio: 60.00%, Deviation: 50.00%
neededClean
false
wordsTotal
210
wordsDialogue
126
49.3562%