Model

Claude 3.0 Sonnet

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-07-19-01J35TC6ST09CR94AMVA183EYN

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
"So, you're telling me we're going to rob a bunch of kids?" Bill whispered, his brow furrowed in concern. Molly rolled her eyes. "Don't be such a wuss. It's not like we're stealing from the little brats themselves. We're just taking the gifts their parents bought them." "But isn't that kind of low?" Bill protested. "I mean, stealing from kids?" "We're not stealing from kids!" Molly hissed. "We're stealing from rich, entitled parents who spoil their kids rotten. It's practically a public service." Bill didn't look convinced. "I don't know, Molly. This seems like a new low, even for us." "Look, do you want to make some serious cash or not?" Molly demanded. "Because this job is a gold mine. Literally. I heard little Timmy's getting a solid gold rocking horse." Bill's eyes widened. "A solid gold rocking horse? For a kid?" Molly nodded smugly. "Exactly. And that's just one of the hauls we'll be making off with. So, are you in or are you out?" Bill hesitated for a moment, then sighed. "Alright, I'm in. But if we get caught, I'm blaming you." Molly grinned. "That's the spirit! Now, let's go crash this kiddie party."
id"gen-40utJTBmVt5SRWSck3RVxuxDauLK" 
total_cost0.0051
upstream_id"msg_01K7zrHs7oM7UonAxdmRZaYy" 
created_at"2024-07-19T15:39:47.085514+00:00" Friday, July 19th, 2024 at 3:39:47 PM GMT+00:00
model"anthropic/claude-3-sonnet:beta" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Anthropic" 
latency7516
moderation_latency(null)
generation_time0
finish_reason"end_turn" 
tokens_prompt68
tokens_completion287
native_tokens_prompt75
native_tokens_completion325
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0051

Evaluation details

Result Evaluator Details Meta Data
99.7443% Matches word count n/a
neededCleanfalse
words196
61.2519% Dialogue to Total Word Ratio
Ratio: 81.63%, Deviation: 8.37%
neededCleanfalse
wordsTotal196
wordsDialogue160
80.4981%