NC Bench
Overview
About
Tests
Models
Model
Claude 3.5 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T99X8A5MNAWCWHA5QZ649
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, Molly, you got the plan?" "Yeah, Bill. It's a piece of cake." "Cake? There better be cake at this party." "Focus, Bill. We're not here for the cake." "Right, right. The presents. How many we talkin'?" "At least twenty. It's some rich kid's bash." "Sweet. How we getting in?" "Through the back. I got us clown costumes." "Clowns? Aw, come on, Molly. I hate clowns." "Tough. It's foolproof. We blend right in." "Fine. What's our exit strategy?" "We stuff the loot in our oversized pants." "Seriously? That's your master plan?" "You got a better idea, genius?" "Yeah, how about we don't rob kids?" "Cold feet, Bill? I thought you were hardcore." "I am! But... it's just... they're kids, y'know?" "Kids with awesome toys we can fence." "True. Alright, I'm in. But I call dibs on any video games." "Deal. Now, let's go over the timing again." "Wait, one more thing." "What now, Bill?" "Can we at least have some cake before we go?"
id
"gen-a1MxjU3szHcYopnNd1IxtuGyXuMO"
total_cost
0.00486
upstream_id
"msg_016PzpwNJxxRAcw3SYmmTaym"
created_at
"2024-07-19T15:38:22.906051+00:00"
Friday, July 19th, 2024 at 3:38:22 PM GMT+00:00
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
18188
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
258
native_tokens_prompt
75
native_tokens_completion
309
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00486
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
164
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
164
wordsDialogue
164
18.3940%