NC Bench
Overview
About
Tests
Models
Model
GPT-4 Turbo
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SKM6DP1SJGB88CN11DR6N
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
Molly peered over the blueprint, whispering, "Alright, Bill. Operation Party Pooper is a go. You snagged the clown costume?" Bill nodded, his face serious beneath a rainbow wig, "Yeah, and you're sure they won't notice me swapping out the magician?" Molly rolled her eyes. "Bill. It's a bunch of five-year-olds. As long as you pull a rabbit out of something, they'll be thrilled." He grimaced. "About that rabbit—" "You didn’t?" "Let’s just say, the pet store was out, but I got creative. You like hamsters, right?" She sighed. "Fine, just stuff some in your sleeves. Now, when the cake comes out, that's our signal, got it?" Bill tapped his nose. "Gotcha. While they're busy with the cake, I tiptoe to the present pile. How am I smuggling them out, though?" Molly flashed a grin. "The stroller. They’ll just think you’re a doting dad." Bill chuckled. "Genius! And for the grand escape?" She pulled out two tiny bicycles. "We ride out in style. They got streamers and everything." Bill burst out laughing. "Molly, we’re too old for this." She shrugged. "But not too old for a little bit of fun."
id
"gen-hOUNhPpRR0feDKeEkTbV23tfDV5G"
total_cost
0.00914
upstream_id
"chatcmpl-9mjmol2cCRzgIbh9WuCfNSuN0R8Y3"
created_at
"2024-07-19T15:26:25.330505+00:00"
Friday, July 19th, 2024 at 3:26:25 PM GMT+00:00
model
"openai/gpt-4-turbo"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
11188
moderation_latency
202
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
282
native_tokens_prompt
68
native_tokens_completion
282
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00914
Evaluation details
Result
Evaluator
Details
Meta Data
93.6496%
Matches word count
n/a
neededClean
false
words
191
3.4008%
Dialogue to Total Word Ratio
Ratio: 76.44%, Deviation: 13.56%
neededClean
false
wordsTotal
191
wordsDialogue
146
48.5252%