NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-19-01J35SM4GMJ9ST3JMGDYG61QGF
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 a giant inflatable unicorn in the backyard. The sound of children’s laughter filled the air, mingling with the whirring of a bubble machine. Molly adjusted her oversized sunglasses, peeking over the unicorn to survey the scene. "Do you see the cake? That’s our entry point," she whispered. Bill, fiddling with a fake clown nose, nodded. "Yeah, but what's the distractor?" Molly rolled her eyes, producing a squeaky rubber chicken from her bag. "This." Bill blinked twice before chuckling softly. "You’re kidding." Molly smirked. "Worked last time, didn’t it?" Bill took a deep breath and straightened his tie. "Okay, on three. One, two, chicken!" Molly tossed the rubber toy into the middle of the yard, and it squeaked loudly as it hit the ground. Instantly, ten kids swarmed it, leaving the gift table unguarded. Bill and Molly darted toward the table like ninjas in unfortunate day-glo outfits. "Which one first?" Bill said, eyeing the gaudy packaging. "Grab the biggest. More stuff," Molly replied, stuffing a giant teddy bear into her duffel bag. In a matter of minutes, the pile of presents had vanished, and Bill and Molly retreated back into the cover of the inflatable. They high-fived silently, the sheer ridiculousness of the heist dawning on them. Molly couldn’t resist a final peek over the unicorn. "Thanks for the memories, kids."
id
"gen-ZZofjGyUKp1G8aJ3UQ2Kll0zduH8"
total_cost
0.00521
upstream_id
"chatcmpl-9mjn5CW6NBTip8moM9ymw1JVumh8b"
created_at
"2024-07-19T15:26:37.577179+00:00"
Friday, July 19th, 2024 at 3:26:37 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
6157
moderation_latency
699
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
327
native_tokens_prompt
67
native_tokens_completion
325
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00521
Evaluation details
Result
Evaluator
Details
Meta Data
0.4920%
Matches word count
n/a
neededClean
false
words
227
65.5486%
Dialogue to Total Word Ratio
Ratio: 18.06%, Deviation: 8.06%
neededClean
false
wordsTotal
227
wordsDialogue
41
33.0203%