NC Bench
Overview
About
Tests
Models
Model
Claude 3.5 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T3PS192QYYP7RNEMQ367Z
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, are you seriously suggesting we rob a kid's party?" "Come on, Bill. Think about it. All those shiny new toys, gift cards, and cash..." "But they're children!" "Exactly! They don't need all that stuff. We're doing them a favor, really." "How do you figure?" "Too many presents spoil the child, Bill. We're teaching them a valuable lesson about materialism." "I don't know... seems risky. What if we get caught?" "By who? A bunch of sugar-high six-year-olds?" "The parents might be there." "Please. They'll be too busy taking photos for Instagram to notice us." "What's our plan then?" "We dress up as clowns." "Clowns? Are you insane?" "It's perfect! We'll blend right in." "I hate clowns." "Suck it up, buttercup. This is our ticket to easy street." "Fine. But I get to be the sad clown." "Whatever floats your boat. Now, here's what we'll do..." "Wait, how are we going to carry all the loot in our clown costumes?" "Ever heard of a magic clown car, Bill?" "You can't be serious." "Dead serious. Now, let's go paint those frowns upside down and get rich!"
id
"gen-JkqckQe2RB8y0HdMLS3fr36tfIne"
total_cost
0.005115
upstream_id
"msg_012Z1p5ogC3CgCtSfed9f4nk"
created_at
"2024-07-19T15:35:23.449257+00:00"
Friday, July 19th, 2024 at 3:35:23 PM GMT+00:00
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
22545
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
269
native_tokens_prompt
75
native_tokens_completion
326
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.005115
Evaluation details
Result
Evaluator
Details
Meta Data
75.1556%
Matches word count
n/a
neededClean
false
words
187
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
187
wordsDialogue
187
55.9718%