NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-02-24-01JMX0FJS4QMRXXY0VKXZWQJSH
Run Details
Model:
Claude 3.7 Sonnet
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.8s
Cost:
$0.005040
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
99.86%
Dialogue to Total Word Ratio
(details)
50.4484%
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
"So, we're really doing this, huh?" Molly's eyes narrowed as she spread the crude map across the table. "Yes ma'am! Operation Birthday Bandit is a go." Bill tapped the X marked 'bouncy castle.' "You realize these are children's presents, right? Stuffed animals and plastic dinosaurs." "And video games! Don't forget the latest PlayStation stuff. Kids are swimming in tech these days." "Still feels wrong." Molly chewed her lip. "Like stealing candy from a baby." "That's literally what we're doing. Except it's wrapped candy. With gift receipts." "What's our entry point again?" "We dress as clowns. Nobody questions clowns at a kid's party." "I hate clowns." "You'll be a clown who hates clowns. Very meta." "And the getaway?" "Ice cream truck. Already hot-wired it." "Bill!" "Kidding! Rented. Legit. So, we grab the loot during the cake cutting when everyone's distracted." "What if a kid sees us?" "We say we're taking them to be wrapped better. Kids are gullible." "We're terrible people." "Terrible people who'll be PlayStation-rich. You in?" "Fine. But I'm not making balloon animals."
id
"gen-1740435345-iMaSnWQJ8H6oh2tezQkW"
upstream_id
"msg_01HcPXiyDCjiXRDkoyfotHDH"
total_cost
0.00504
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:15:56.236563+00:00"
2/24/2025, 10:15:56 PM
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
541
moderation_latency
(null)
generation_time
5941
tokens_prompt
68
tokens_completion
258
native_tokens_prompt
75
native_tokens_completion
321
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
0.00504
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
174
99.86%
Dialogue to Total Word Ratio
Ratio: 88.07%, Deviation: 1.93%
neededClean
false
wordsTotal
176
wordsDialogue
155
50.4484%