NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35T3B7FFG20FY1GTWS28C2F
Run Details
Model:
Claude 3.5 Sonnet
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
17.3s
Cost:
$0.004980
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
55.9718%
Overall
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. A children's party?" "Dead serious, Bill. Think about it. All those shiny new toys, games, and gadgets, just sitting there waiting for us." "But... it's for kids. Isn't that a bit, I don't know, low?" "Low? It's brilliant! Who'd suspect a heist at little Timmy's birthday bash?" "I dunno, Mol. What's our cover? We can't exactly blend in with the ankle-biters." "Easy. We're the entertainment. You'll be the clown." "Oh, hell no. I am not wearing a red nose and floppy shoes." "Fine, you can be the magician. I'll be your lovely assistant." "And how exactly do we snatch the loot with all those rugrats running around?" "Simple. We create a distraction. You do your magic act, I'll slip away and bag the goods." "What if we get caught?" "By who? A bunch of sugar-high six-year-olds?" "Their parents might object to us robbing their precious little ones." "Details, Bill. Don't be such a party pooper. Are you in or not?" "...Fine. But I'm not pulling a rabbit out of a hat." "Deal. Now, let's go shopping for your top hat and cape."
id
"gen-cb3k3rfjkPrggDOAdX7FWr1GeQeY"
total_cost
0.00498
upstream_id
"msg_01SM92bVcmtbcu97bmkJoutD"
created_at
"2024-07-19T15:35:06.328362+00:00"
7/19/2024, 3:35:06 PM
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
17271
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
275
native_tokens_prompt
75
native_tokens_completion
317
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00498
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
191
wordsDialogue
191
55.9718%