NC Bench
Overview
About
Tests
Models
Model
Claude 3.5 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T9K46753DFDBW36AMVNVY
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, you can't be serious," Bill whispered, his eyes wide with disbelief. "Dead serious, Bill. Think about it: mountains of presents, all wrapped up nice and tidy." "But it's a kids' party! We can't steal from children!" "Sure we can. They're spoiled brats anyway. Besides, their parents will just buy them new stuff." "I don't know, Molly. It feels... wrong." "Wrong? We rob banks for a living, and suddenly you've grown a conscience?" "That's different. Banks are insured. These are personal gifts." "Personal, schmersonal. Look, it's the perfect setup. We dress as clowns, blend right in." "Clowns? I hate clowns." "Everybody hates clowns. That's why it's perfect. No one will look twice at us." "And then what? We just grab the gifts and run?" "No, you nincompoop. We stuff them in our oversized clown pants. They'll never suspect a thing." "This is crazy, Molly. Absolutely bonkers." "Crazy like a fox, my friend. So, are you in or out?" Bill sighed heavily. "Fine. But if we get caught, I'm blaming you." "That's the spirit! Now, let's go shopping for some big, floppy shoes."
id
"gen-lisKzKcTAgJjZGC9nk9xQfVtzy1n"
total_cost
0.005085
upstream_id
"msg_01GRRNFcotiKZGPzQ4QHJXFJ"
created_at
"2024-07-19T15:38:25.621517+00:00"
Friday, July 19th, 2024 at 3:38:25 PM GMT+00:00
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
11824
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
275
native_tokens_prompt
75
native_tokens_completion
324
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.005085
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
182
95.9631%
Dialogue to Total Word Ratio
Ratio: 94.51%, Deviation: 4.51%
neededClean
false
wordsTotal
182
wordsDialogue
172
65.4826%