NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-11-04-01JBW94WH1EXB21DZTYXVWKM3K
Run Details
Model:
Claude 3.5 Haiku
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.3s
Cost:
$0.001312
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
5.25%
Dialogue to Total Word Ratio
(details)
36.6774%
Overall
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 leaned back in the rickety kitchen chair, twirling a lockpick between her fingers. Bill was hunched over a crude map of the suburban birthday party venue, his forehead creased with concentration. "You really think this is worth our time?" Molly asked, arching an eyebrow. Bill looked up. "Trust me, rich suburban kids get the good stuff. PlayStation 5s, limited edition LEGO sets, designer electronics." "We're stealing from children?" Molly snorted. "Technically, we're stealing from their parents," Bill corrected. "Besides, these are the kind of parents who buy their kids everything and appreciate nothing." Molly drummed her fingers on the table. "And the security?" "One weekend babysitter, grandparents in the corner eating cake, zero actual supervision." Bill grinned. "It's like they're begging us to rob them." "That's cold, even for us," Molly chuckled. "Cold? This is strategic wealth redistribution," Bill said, dramatically air-quoting. "Plus, these kids won't even remember half the gifts by next week." Molly rolled her eyes. "Fine. But I'm picking the getaway vehicle, and if it's not smooth, this whole plan is your fault." Bill raised his coffee mug. "To children's birthday heists."
total_cost
0.001312
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
5.25%
Dialogue to Total Word Ratio
Ratio: 63.10%, Deviation: 13.10%
neededClean
false
wordsTotal
187
wordsDialogue
118
36.6774%