NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-02-24-01JMX0VMFF7NCHWYBAMAEYBR6P
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, Bill, what's the plan?" Molly asked, fiddling with her lock picks. "We go in while the magic show's happening. All eyes on the clown." "It's not a clown, it's a magician. Different skill sets entirely." Bill rolled his eyes. "Whatever. Kids screaming, parents filming, nobody watching the present table. We're in and out in two minutes." "The party's at three, right?" "Yeah. Little Timmy's sixth birthday extravaganza." Molly winced. "Does it bother you we're stealing from a six-year-old?" "Does it bother you that last week we stole dentures from a retirement home?" "Those were solid gold! This is different. It's a kid." "A kid who's getting forty presents he'll forget about in a week." "Fair point. What's our exit strategy?" "Back door through the kitchen." "And if someone sees us?" "We're the entertainment's assistants, grabbing props." "Brilliant. What if they ask what props?" "The... disappearing presents trick?" Molly snorted. "You're terrible at this." "Hey, I got us the floor plan, didn't I?" "From a Chuck E. Cheese website." "It's basically the same layout." "Right. Let's go rob some children."
id
"gen-1740435739-kyf9VjJMvssjigpScLKO"
upstream_id
"msg_01NFxKShq8uoXqRnoj6dqpmv"
total_cost
0.00507
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:22:27.087171+00:00"
Monday, February 24th, 2025 at 10:22:27 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
962
moderation_latency
(null)
generation_time
6052
tokens_prompt
68
tokens_completion
267
native_tokens_prompt
75
native_tokens_completion
323
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
0.00507
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
182
99.9045%
Dialogue to Total Word Ratio
Ratio: 91.76%, Deviation: 1.76%
neededClean
false
wordsTotal
182
wordsDialogue
167
67.4533%