NC Bench
Overview
About
Tests
Models
Model
GPT-4 Turbo
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35SV1JXEZEV0FTMYP04TKA9
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 ducked under a streamer-adorned fence, clipboard in hand, her eyes scanning the lively backyard. "Okay, Bill, focus. We hit the gift table during the piñata session. Chaos is our BFF." Bill, munching on a stolen cupcake, nodded, frosting smeared across his cheek. "Right. Kids whack, we pack.” “Exactly,” Molly replied, crouching beside a bush shaped like a bunny. “You grab the big boxes, I’ll snag the smaller, shinier ones." “What if someone spots us?” Bill's voice was muffled by his cupcake. Molly rolled her eyes. “We’re grown adults hiding behind topiary, Bill. Just act like you lost a kid or something." “Can’t we just buy presents like normal crooks?” “We’re not normal, we’re innovative.” Molly checked her watch. “Showtime’s in three minutes. Ready?" Bill, finishing his last bite, wiped his hands on his jeans. “Born ready. And afterwards, I want cake.” “If we pull this off, you’ll have enough cake to last till Christmas.” The sounds of children counting down echoed across the yard, a candy-filled piñata swinging perilously. "Go time," Molly whispered, as they dashed forward amid a flurry of cheering and blindfolded swings.
id
"gen-kjfCmZBKtveEZ0tP8E7Fau7TPVYe"
total_cost
0.00905
upstream_id
"chatcmpl-9mjqjDgZvXUUrBdR3b5pZzRjVAdc8"
created_at
"2024-07-19T15:30:29.647999+00:00"
Friday, July 19th, 2024 at 3:30:29 PM GMT+00:00
model
"openai/gpt-4-turbo"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
12103
moderation_latency
354
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
279
native_tokens_prompt
68
native_tokens_completion
279
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00905
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
188
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
188
wordsDialogue
94
90.6364%