NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-06-01J4MXXZ8ZQW9XC1VNW8PZZMHE
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
"Bill, you sure about this? A children's party?" "Molly, think about it. Who's gonna suspect a couple of clowns?" "Clowns? You want us to dress up?" "You got a better idea? Kids love clowns." "Yeah, kids love clowns that hand out balloons, not steal their presents." "We’re not stealing from kids. We're... liberating excess toys from wealthy parents." "That’s a creative way to put it. Still feels Grinchy." "Grinchy heists have low security. No one’s guarding a pile of toys." "And when Trudy turns eight again, she's gonna want her pink unicorn back." "That's why we use the decoy present switcheroo—leave a dud, take the plush." "Your decoys better be good. Kids notice these things." "Easy-peasy. Who’s gonna be mad? A five-year-old and a piñata?" "Piñatas have nothing on angry moms, Bill." "We blend in. Cause a little chaos and voila! Be home by dinner." "Chaos? Like puppies in tutus?" "Precisely. Distract with cuteness, then make our move." "Good they won't suspect the funny clown and tutu act." "We're harmless fun! Smile big, wave, grab and go." "And if a kid hugs my leg, Bill?" "Count to three, pat their head, and send 'em on their way." "Misdirection with a smile. I can handle that." "Welcome to the heist circuit, Molly."
id
"gen-RKqJCujfYwiI1fsluUc5ndzzGkpR"
total_cost
0.0033375
upstream_id
"chatcmpl-9tNEMdKeyowfBbF9U0bQZTBWsDnCu"
created_at
"2024-08-06T22:46:09.478077+00:00"
Tuesday, August 6th, 2024 at 10:46:09 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3555
moderation_latency
204
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
326
native_tokens_prompt
67
native_tokens_completion
317
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0033375
Evaluation details
Result
Evaluator
Details
Meta Data
60.2752%
Matches word count
n/a
neededClean
false
words
215
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
215
wordsDialogue
215
48.5316%