NC Bench
Overview
About
Tests
Models
Model
Claude 3.5 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35T6KQHFNTZVSHH4Y2GC76C
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 peered through her binoculars at the colorful banners fluttering in the backyard. "I count at least twenty gifts, Bill. This is gonna be a good haul." Bill fidgeted nervously beside her. "I don't know, Mol. Stealing from kids? Seems kinda low, even for us." "Oh, grow a spine," Molly scoffed. "These brats are probably spoiled rotten anyway. We're doing their parents a favor." "If you say so," Bill mumbled. "What's the plan?" Molly grinned mischievously. "We go in as party entertainers. I'll be a clown, you'll be a magician." "A magician?" Bill groaned. "I don't know any tricks!" "Just wave your hands around and say 'abracadabra' a lot. While you distract them, I'll stuff the presents in my oversized clown pants." Bill sighed. "Fine. But if we get caught, I'm blaming you." "Relax, partner," Molly said, patting his shoulder. "What could possibly go wrong at a six-year-old's birthday party?" As if on cue, a piercing shriek erupted from the yard, followed by the unmistakable sound of a cake hitting the ground. "On second thought," Molly muttered, "maybe we should sit this one out."
id
"gen-YRYKB8LJfjpXyiO4FtvkXdOnQf0y"
total_cost
0.00522
upstream_id
"msg_017f3L3SnBriGiTDWv8yx9VJ"
created_at
"2024-07-19T15:36:50.202733+00:00"
Friday, July 19th, 2024 at 3:36:50 PM GMT+00:00
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
14110
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
275
native_tokens_prompt
75
native_tokens_completion
333
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00522
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
0.0004%
Dialogue to Total Word Ratio
Ratio: 68.82%, Deviation: 18.82%
neededClean
false
wordsTotal
186
wordsDialogue
128
34.0513%