NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-02-24-01JMWZYZ0BT6F65NAE90W6NNAE
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
"So, Bill, we hit the birthday party at exactly 2:15," Molly said, twirling her lock pick between her fingers. "That's when they'll be singing Happy Birthday." "I don't know, Mol. Kids' presents? Even for us, that's low." Bill shifted uncomfortably on the park bench. "Low? These aren't regular kids. They're Westfield kids. You know what I got for my sixth birthday? Socks." "Still..." "Little Timmy Matthews is getting a PlayStation 5, two iPhones, and a dirt bike." Bill whistled. "Rich blood." "Filthy rich. And the parents? Insurance fraudsters. Remember that 'accidental' yacht fire last summer?" "The one where they conveniently removed their Picasso first?" "Exactly. We're basically Robin Hood here." "Robin Hood stole from the rich and gave to the poor." "And we're poor, Bill! Connect the dots!" "What's our exit strategy?" "Ice cream truck. I got Miguel to park out back. We load the presents in with the popsicles." "That's... actually brilliant." "I know. You in?" Bill sighed. "Fine. But if one kid cries, I'm out." "Trust me, these kids won't even notice with their bounce castle and petting zoo."
id
"gen-1740434801-FcKFlBWrFd8BhQl8xKwT"
upstream_id
"msg_01Ut9H6rr8qzQNxJCkWFPS4P"
total_cost
0.005025
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:06:48.275204+00:00"
Monday, February 24th, 2025 at 10:06:48 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
396
moderation_latency
(null)
generation_time
5854
tokens_prompt
68
tokens_completion
274
native_tokens_prompt
75
native_tokens_completion
320
native_tokens_reasoning
0
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.005025
Evaluation details
Result
Evaluator
Details
Meta Data
27.1658%
Matches word count
n/a
neededClean
false
words
181
99.9879%
Dialogue to Total Word Ratio
Ratio: 88.95%, Deviation: 1.05%
neededClean
false
wordsTotal
181
wordsDialogue
161
63.5768%