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
2024-07-19-01J35TAF0MFCSB9RT1TBMW87RB
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 the clown costume?" "Of course. And you?" "Princess dress, tiara, the whole shebang." "Perfect. We walk in, act like we're part of the entertainment." "Exactly. Then, while they're distracted with the magic show, we grab the presents." "Where do we stash them?" "In the big piƱata. No one will suspect a thing." "Smart. What if someone catches on?" "That's why we have the backup plan." "The balloon animals?" "Yes, Bill, the balloon animals. We make a quick exit, leaving a trail of balloon animals as a distraction." "Got it. And the getaway car?" "Parked two blocks away. We leave through the back gate." "Sounds foolproof. What time do we start?" "Party begins at 3 PM. We go in at 3:15, right when the sugar rush hits." "Alright, Molly. Let's do this." "Remember, Bill, keep it light, keep it fun. We're just two entertainers making kids happy." "And stealing their presents." "Exactly. Now, let's go make some kids cry." "Best heist ever."
id
"gen-igkSaUkr7n8L8dsGTdeEawcFBtu3"
total_cost
0.004835
upstream_id
"chatcmpl-9mjysZXuNnLJwZMV6yDpKChGdriid"
created_at
"2024-07-19T15:38:50.312344+00:00"
Friday, July 19th, 2024 at 3:38:50 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
7681
moderation_latency
322
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
307
native_tokens_prompt
67
native_tokens_completion
300
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.004835
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
205
wordsDialogue
205
68.0824%