NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-02-24-01JMX0NA7YWE0EDKCF30BNEH0W
Run Details
Model:
Claude 3.7 Sonnet
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.2s
Cost:
$0.004890
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
99.72%
Dialogue to Total Word Ratio
(details)
59.9532%
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, let me get this straight, Molly. You want us to rob a child's birthday party?" Bill adjusted his ski mask nervously. "Not just any birthday party, Bill. Little Timmy Henderson's tenth birthday extravaganza. Do you know who his father is?" Molly spread blueprints across the table. "The hedge fund guy?" "Precisely. Those presents won't be water guns and comic books. We're talking gaming consoles, designer clothes, maybe even a dirt bike." Bill whistled. "Still feels wrong." "What's wrong is a ten-year-old getting a solid gold tablet when we can barely make rent. Besides, we're teaching him a valuable life lesson about materialism." "Ah yes, nothing says 'childhood development' like trauma." "Don't be dramatic. We'll go in during the magician's act—kids distracted, parents taking photos." "Security?" "One bored teenager checking invitations. We'll say we're the clowns." "We don't have costumes." "Already handled. Your outfit's in the car." "Please tell me it's not—" "Full rainbow wig, red nose, the works." "I hate you." "Love you too. And Bill?" "What?" "If you steal a slice of cake, I'll kill you myself."
id
"gen-1740435533-vzf4jSowKkBedvPGrESt"
upstream_id
"msg_013u1C8jruHwRtLxVhuvFzat"
total_cost
0.00489
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:19:00.510204+00:00"
2/24/2025, 10:19:00 PM
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
496
moderation_latency
(null)
generation_time
5477
tokens_prompt
68
tokens_completion
264
native_tokens_prompt
75
native_tokens_completion
311
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
0.00489
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
99.72%
Dialogue to Total Word Ratio
Ratio: 92.31%, Deviation: 2.31%
neededClean
false
wordsTotal
182
wordsDialogue
168
59.9532%