NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-02-24-01JMX0BD3WCV5A15YQKDFTAAA0
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 hunched over the diner table, stirring her coffee with unnecessary vigor. "So Bill, I've been casing this birthday party at the Hendersons'. Little Timmy, turning six. Prime target." Bill choked on his pancakes. "A kid's birthday party? That's low, even for us." "Not the kid, dummy. The presents." Molly's eyes gleamed. "Rich neighborhood, thirty kids invited. We're talking premium haul." "How do we get in?" Bill dabbed syrup from his chin. "I draw the line at clown costumes." Molly slid a flyer across the table. "They hired entertainment. Magician canceled last minute." "You want us to perform magic tricks? I can barely pull off card counting." "Relax. We do two simple tricks, create a distraction during cake time, then raid the gift table." She tapped her watch. "Fifteen minutes, in and out." Bill sighed dramatically. "Fine. But if one kid cries because of us, I'm out." "The only tears will be Timmy's when he realizes his Nintendo Switch walked away." Molly grinned wickedly. "Now, how's your rabbit-from-a-hat technique?" Bill groaned. "I'm allergic to rabbits." "Perfect," Molly laughed. "That'll be distraction number one."
id
"gen-1740435207-hS4AUoKEREacoD3qG1rg"
upstream_id
"msg_014jn9wtu8RpWCwAcgC7rGYN"
total_cost
0.00519
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:13:35.204415+00:00"
Monday, February 24th, 2025 at 10:13:35 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
688
moderation_latency
(null)
generation_time
6076
tokens_prompt
68
tokens_completion
272
native_tokens_prompt
75
native_tokens_completion
331
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
0.00519
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
0.0000%
Dialogue to Total Word Ratio
Ratio: 74.73%, Deviation: 24.73%
neededClean
false
wordsTotal
186
wordsDialogue
139
34.0511%