NC Bench
Overview
About
Tests
Models
Model
GPT-4 Turbo
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35TABA2WVX6XJ6KNY11JADD
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 peered over the fence, her eyes scanning the colorful backyard filled with balloons and streamers. Bill crouched next to her, balancing a slice of pizza he'd swiped from a passing waiter. "Look at 'em, oblivious and stuffing their faces with cake," Molly whispered, gesturing towards the children giggling around a mountain of presents. Bill grunted, eyes glued to the candy-strewn piñata. "You got the distraction ready?" "Yeah, confetti bomb in T-minus two minutes. When I say 'oops'—that's your cue to grab as many as you can." Bill nodded, stuffing the last of his pizza into his mouth. "Oops then dash, got it." "And be stealthy. If a six-year-like Lara spots you, we're toast." "Question," Bill said, eyebrows knit together, "any chance I can grab a toy for myself? There's a remote control car I've had my eye on." Molly frowned. "Focus, Bill. Loads of loot and you want a toy car?" "Hey, even thieves need playtime." The confetti bomb exploded suddenly, scattering shimmers like a fireworks display. "Oops," Molly muttered under her breath. Bill bolted, arms spread wide, as he swooped towards the stack of gift-wrapped boxes like a hawk, leaving Molly shaking her head, half-amused, half-exasperated.
id
"gen-Lt0lgiHeLi85wpneu7vjv1JzGFu1"
total_cost
0.00941
upstream_id
"chatcmpl-9mjyoWHj9Sswi326wmtfpu5zfMybw"
created_at
"2024-07-19T15:38:51.135997+00:00"
Friday, July 19th, 2024 at 3:38:51 PM GMT+00:00
model
"openai/gpt-4-turbo"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
12396
moderation_latency
220
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
291
native_tokens_prompt
68
native_tokens_completion
291
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00941
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
90.5714%
Dialogue to Total Word Ratio
Ratio: 44.39%, Deviation: 5.61%
neededClean
false
wordsTotal
205
wordsDialogue
91
94.9742%