NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-08-06-01J4MXY0MZ9X097K8XW28R85RQ
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 dimly lit basement was cluttered with blueprints and half-eaten pizza boxes. Molly leaned over the table, her eyes gleaming with mischief. "Bill, you ever crash a kid's party before?" she asked, a sly grin spreading across her face. Bill chuckled, adjusting his cap. "Not since I was ten, and even then, I was more interested in the cake than the presents." Molly tapped a finger on the map. "Focus, Bill. This isn't about cake. It's about the loot. Those kids won't know what hit 'em." Bill nodded, trying to suppress a laugh. "Right. So, we sneak in during the magic show. Everyone's eyes will be on the rabbit, not us." "Exactly," Molly replied, her voice brimming with excitement. "And while they're distracted, we grab the goods and vanish like smoke." Bill raised an eyebrow. "You sure about this? I mean, it's a kid's party. What if we get caught?" Molly shrugged, her confidence unwavering. "Then we blame it on the clown. Who's gonna believe a clown, anyway?" Bill snorted, shaking his head. "Alright, let's do it. But if I end up with a balloon animal, I'm blaming you." Molly winked. "Deal. Now, let's make some kids cry."
id
"gen-bFyVveFuySfDnO26erEZxkWMkXcY"
total_cost
0.0029375
upstream_id
"chatcmpl-9tNENg5EHEgFnPji3itUcUWIqOZ09"
created_at
"2024-08-06T22:46:10.444016+00:00"
Tuesday, August 6th, 2024 at 10:46:10 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3273
moderation_latency
160
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
286
native_tokens_prompt
67
native_tokens_completion
277
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0029375
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
199
0.0000%
Dialogue to Total Word Ratio
Ratio: 62.81%, Deviation: 52.81%
neededClean
false
wordsTotal
199
wordsDialogue
125
49.9995%