NC Bench
Overview
About
Tests
Models
Model
GPT-4 Turbo
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T7WKXRMYK0EXMD8X1RH5V
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
“Bill, you absolutely sure about this? A children's party?” Molly whispered, adjusting her oversized clown hat. “Molly, trust me, it’s foolproof. Kids are distracted, parents are relaxed, loads of presents. Easy pickings!” Bill reassured her, peeking from behind the tree. “But what about the kids, Bill?” Molly fretted, fiddling with a fake nose. “Look, we don’t take the teddy bears or anything—just the fancy boxes. The ones likely hiding the tech stuff,” Bill plotted, eyes gleaming. “Tech stuff at a kid's party?” “You'd be surprised what these fancy folks gift. Saw a kid get a drone last week!” Bill chuckled quietly. Molly sighed, “And you’re sure the magic show is the best time?” “Absolutely,” Bill nodded. “Everyone’s eyes on the magician. We swoop in, snatch, and scoot. Simple.” “And the getaway?” “Via the petting zoo. We blend in with the departing crowd, then hop in the van. Who suspects the clowns?” Bill smirked, tugging at his polka dot tie. Molly looked about nervously, “Okay, let’s be the best darn clowns they ever saw.” Bill grinned, “Just stick to the plan. Smile big, laugh hard, and walk away richer.”
id
"gen-i5SALv0Qkj7WaMh6GEX2eP80sRiE"
total_cost
0.00908
upstream_id
"chatcmpl-9mjxW0TqEvNbJ0JzTT7psLCPoa69C"
created_at
"2024-07-19T15:37:29.570495+00:00"
Friday, July 19th, 2024 at 3:37:29 PM GMT+00:00
model
"openai/gpt-4-turbo"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
11377
moderation_latency
231
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
280
native_tokens_prompt
68
native_tokens_completion
280
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00908
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
189
0.7549%
Dialogue to Total Word Ratio
Ratio: 75.13%, Deviation: 14.87%
neededClean
false
wordsTotal
189
wordsDialogue
142
43.5676%