NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-19-01J35TEP6DTX2VF75E63WVVCRH
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Molly and Bill crouched behind the bushes, peering through the gaps at the colorful chaos of the children's party. Balloons bobbed in the breeze, and the sound of laughter filled the air. Molly adjusted her oversized sunglasses and nudged Bill. "Are you sure this is a good idea?" she whispered, her eyes darting around. Bill grinned, his teeth flashing in the sunlight. "Piece of cake. We go in, grab the presents, and get out. No one will even notice." Molly frowned, glancing at the pile of brightly wrapped gifts under the tree. "But it's a kids' party, Bill. Isn't this a bit... low?" Bill shrugged, pulling a clown mask from his bag. "Desperate times, Molly. Besides, think of it as redistributing joy." Molly sighed, reluctantly pulling out her own mask, a garish unicorn. "Fine. But if we get caught, I'm blaming you." Bill chuckled, adjusting his mask. "Deal. Now, remember the plan. You distract the kids with your balloon animals, and I'll handle the presents." Molly rolled her eyes but nodded. "Alright, let's do this." They slipped out from behind the bushes, blending into the party with surprising ease. Molly started twisting balloons into shapes, drawing the children's attention, while Bill edged closer to the gift pile, his eyes gleaming with anticipation.
id
"gen-KeBAfOhO27hJ8Y2OUMtLwhIXN3hR"
total_cost
0.004625
upstream_id
"chatcmpl-9mk17NkykhVKZjuNglysbjqVsCbZS"
created_at
"2024-07-19T15:41:06.398403+00:00"
Friday, July 19th, 2024 at 3:41:06 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
5184
moderation_latency
239
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
293
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
81.2727%
Matches word count
n/a
neededClean
false
words
212
0.0000%
Dialogue to Total Word Ratio
Ratio: 36.32%, Deviation: 26.32%
neededClean
false
wordsTotal
212
wordsDialogue
77
40.6364%