NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SJN264V7NCKFAZY0P1J97
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
"Alright, Bill, you got the plan?" "Yeah, Molly, but remind me why we're stealing from a kids' party again?" "Because, Bill, nobody expects thieves at a children's party. It's the perfect cover." "Right, right. So, we sneak in dressed as clowns?" "Exactly. You got the costumes?" "Yeah, but mine's a bit tight. I look like a sausage in a rainbow casing." "Perfect. The more ridiculous, the better. Now, what's the first step?" "We blend in with the entertainment. You juggle, I do balloon animals." "Good. And while the kids are distracted?" "We scope out the presents. Find the biggest pile." "Right. Then we create a diversion. Any ideas?" "How about a fake magic trick gone wrong? Kids love chaos." "Brilliant. I'll pretend to pull a rabbit out of a hat, and you make it explode with confetti." "Got it. And during the chaos, we grab the presents and stash them in the clown car." "Exactly. And if anyone gets suspicious?" "We blame it on the other clown. Classic misdirection." "Perfect. Now, remember, no real rabbits. Last time was a disaster." "Agreed. No real rabbits. Just confetti and chaos." "Alright, Bill. Let's go make some kids cry." "And get rich doing it, Molly."
id
"gen-sHA54QzvyjFoUuc2c9iL2TZUd7nQ"
total_cost
0.004625
upstream_id
"chatcmpl-9mjmIXjByUjssGT5NG6VvfKs7oCHO"
created_at
"2024-07-19T15:25:47.228019+00:00"
Friday, July 19th, 2024 at 3:25:47 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
4854
moderation_latency
164
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
290
native_tokens_prompt
67
native_tokens_completion
286
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.004625
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
202
wordsDialogue
202
68.3860%