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
2024-08-06-01J4MXRH8W5DZF2KFPXGT58G8D
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, what's the plan here?" "Molly, it's simple. We waltz into the party like we're the hired clowns." "Clowns? Bill, I can't juggle to save my life!" "That's the beauty of it, Molly. We don't need to do anything but look the part." "And how do we even get in?" "We say we're from the 'Chuckles and Bubbles' agency. They don't know the difference!" "Okay, fine. But how do we grab the presents without creating a scene?" "Easy peasy. You distract the kids with balloon animals." "Bill, you know my balloon animals look more like balloon blobs." "Exactly, Molly. They'll be so confused, they'll never notice me grabbing the loot." "And then what? The parents won't just let us walk out with piles of gifts!" "We hit 'em with the good old disappearing act." "Disappearing act? What are we, magicians now?" "Close enough. We have a getaway vehicle, remember?" "The rusty old van with 'Bakery' painted on the side?" "Precisely! No one suspects a bakery van at a kid's party. It's foolproof." "Foolproof, huh? Just like the time we tried to steal that giant teddy bear?" "Hey, that was a learning experience, Molly. Now we're seasoned professionals." "Alright, Bill. Let's make some kids very confused and some parents quite grumpy."
id
"gen-JSkZ6oT0HeLyjSgmZHFpXAwXwW5y"
total_cost
0.0031375
upstream_id
"chatcmpl-9tNBTQRYvmcD3gBhtqrduoGrGYsSh"
created_at
"2024-08-06T22:43:11.281322+00:00"
Tuesday, August 6th, 2024 at 10:43:11 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3661
moderation_latency
214
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
312
native_tokens_prompt
67
native_tokens_completion
297
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0031375
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
211
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
211
wordsDialogue
211
61.5841%