NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-02-24-01JMX1V0RBGD05KQQ29WYDSGBF
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 a child's birthday party?" Molly raised an eyebrow. "That's what we've come to?" "Listen, it's genius." Bill spread the crude crayon invitation on the table. "The Franklin kid is turning six. Rich parents, richer guests. Those presents aren't just teddy bears." "We're stealing from children now. Wonderful." "Not children. Adults who buy overpriced garbage for children who won't appreciate it." "How do we get in?" Molly asked, twirling her lock pick. "We're the clowns." "Clowns? I don't do clown." "Well, princess, times are tough. I've got the costumes in the car." "This is a new low, Bill. Even for us." "Think of it as redistribution of wealth. From their toy chests to our pockets." "And how exactly do we exit with armfuls of presents?" "That's the beauty part," Bill grinned. "We're performing the magic act. Things are supposed to disappear." Molly sighed. "If I end up on some suburban mom's Instagram making balloon animals, I swear to God..." "Relax. We'll be in and out in thirty minutes. Just follow my lead and smile. Kids love smiles." "I hate you." "Perfect. That's exactly the kind of enthusiasm I'm looking for."
id
"gen-1740436767-ODJYE03pDepwvXtDMprG"
upstream_id
"msg_01Qc1My4tJqJVJNxXk8UieRa"
total_cost
0.0051
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:39:35.150255+00:00"
Monday, February 24th, 2025 at 10:39:35 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
303
moderation_latency
(null)
generation_time
6329
tokens_prompt
68
tokens_completion
272
native_tokens_prompt
75
native_tokens_completion
325
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
0.0051
Evaluation details
Result
Evaluator
Details
Meta Data
90.4837%
Matches word count
n/a
neededClean
false
words
190
99.8038%
Dialogue to Total Word Ratio
Ratio: 87.89%, Deviation: 2.11%
neededClean
false
wordsTotal
190
wordsDialogue
167
95.1437%