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
2024-07-19-01J35SNDGZB9HXCY4SWZ7C9SGY
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 children's party again?" "Because, Bill, no one expects it. Plus, kids' presents are easy to fence." "Right, right. So, what's the first step?" "We blend in. You got your clown costume ready?" "Of course. And you?" "Princess outfit, complete with tiara. We'll be the life of the party." "Okay, so we get in, then what?" "We mingle. You distract the kids with balloon animals." "And you?" "I'll be charming the parents, making sure they don't suspect a thing." "Got it. Then we meet by the gift table?" "Exactly. I'll create a diversion, maybe spill some punch." "And I grab the presents and stash them in the getaway car." "Perfect. But remember, we have to be quick. Kids have short attention spans." "Right. What if someone catches on?" "Improvise. You're a clown, make them laugh." "And you?" "I'll use my princess charm. No one suspects a princess." "Okay, Molly, but what if the kids start crying?" "Then we make a quick exit. We can't have crying kids ruining our heist." "Got it. So, we're all set?" "All set. Let's go steal some joy, Bill." "Or at least their presents."
id
"gen-bMagrmTCjnOQ4S0jSFrcDUQMpqaO"
total_cost
0.004655
upstream_id
"chatcmpl-9mjnkX2ZvFDrvQIBANZxdf9EJFfyj"
created_at
"2024-07-19T15:27:21.737826+00:00"
Friday, July 19th, 2024 at 3:27:21 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
8841
moderation_latency
166
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
297
native_tokens_prompt
67
native_tokens_completion
288
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.004655
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
204
wordsDialogue
204
68.2661%