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

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_cost0.00914
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_id182717
streamedfalse
cancelledfalse
provider_name"OpenAI" 
latency11188
moderation_latency202
generation_time0
finish_reason"stop" 
tokens_prompt68
tokens_completion282
native_tokens_prompt68
native_tokens_completion282
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.00914

Evaluation details

Result Evaluator Details Meta Data
93.6496% Matches word count n/a
neededCleanfalse
words191
3.4008% Dialogue to Total Word Ratio
Ratio: 76.44%, Deviation: 13.56%
neededCleanfalse
wordsTotal191
wordsDialogue146
48.5252%