NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-08-06-01J4MXR6EHEH3T4BEBEMY9PJ41
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
The moon hung low, casting a silvery glow upon the backyard teeming with colorful balloons and streamers. Molly and Bill crouched behind a row of hedges, plotting their whimsical caper with as much seriousness as their profession allowed. "This is, without doubt, the dumbest job we've ever taken," Molly muttered, adjusting her mask of questionable discretion, shaped like a duck. Bill chuckled softly, peeking through the leaves. "Lighten up, Molly. It's a party. How hard can stealing kids' presents be?" "Imagine explaining this when we get caught. 'Yes, officer, we were just borrowing them for future references,' right?" Bill waved a hand dismissively. "We'll be out before they even notice. Quick like bunnies." “Bunnies, Bill? Really? We're masters of crime!" Molly pointed to the towering cake on a folding table. "Think we can grab a slice, too?" Bill shrugged. "Eh, why not? We're already crashing this shindig. Might as well crash hard." Molly rolled her eyes but stifled a grin. "Alright, what's the plan, maestro?" Bill grinned, pulling out a plastic fork. "The usual—larceny with a dollop of frosting." With a final nod, they slunk from their leafy cover, a pair of shadowy titans descending into the bright, bubbling chaos of sugar-fueled revelry.
id
"gen-UNgAASW7WJFUgDqwdXur5J6v5cci"
total_cost
0.0030875
upstream_id
"chatcmpl-9tNBIyZxWCD6DBwke7S7FyBrAPAF9"
created_at
"2024-08-06T22:43:00.600395+00:00"
Tuesday, August 6th, 2024 at 10:43:00 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
4065
moderation_latency
201
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
302
native_tokens_prompt
67
native_tokens_completion
292
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0030875
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
0.0000%
Dialogue to Total Word Ratio
Ratio: 44.39%, Deviation: 34.39%
neededClean
false
wordsTotal
205
wordsDialogue
91
49.6885%