NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-06-01J4MXVJXQP2GDDM8DKXRW3P68
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 got the clown costume ready?" "Of course, Molly. You think I’d forget the big red nose?" "Good. We need to blend in with the entertainment." "And the balloon animals. I’ve been practicing." "Great. Remember, we’re not here for the cake." "Right, right. We’re here for the presents." "Exactly. You distract the kids with your juggling." "Juggling? I thought I was doing magic tricks." "Bill, we went over this. Juggling first, then magic." "Fine, but what if they ask for a rabbit out of a hat?" "Improvise. Use a sock or something." "A sock rabbit? That’s a new one." "Just keep them busy. I’ll handle the gift table." "How are you going to carry all those presents?" "Got a big bag. Like Santa, but cooler." "Santa doesn’t steal, Molly." "Details, Bill. Focus on the plan." "Okay, okay. What if a kid catches us?" "Tell them it’s part of the act." "And if a parent catches us?" "Run. Fast." "Right. And the exit strategy?" "Back door, left of the bouncy castle." "Got it. You sure this will work?" "Positive. Kids love clowns." "Hope they love juggling too." "They will, Bill. They will." "Alright, let’s do this." "On three. One, two, three."
id
"gen-FtTrjIVVXxN5taKzBxCnTzVYYqQh"
total_cost
0.0032275
upstream_id
"chatcmpl-9tND5mwG0aYMGlrhEto68VW09cANU"
created_at
"2024-08-06T22:44:51.404904+00:00"
Tuesday, August 6th, 2024 at 10:44:51 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3775
moderation_latency
217
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
305
native_tokens_prompt
67
native_tokens_completion
306
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0032275
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
201
wordsDialogue
201
68.3935%