NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2025-02-24-01JMX1MTR1DYW87D45XSH69ZYX
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 drummed her fingers on the steering wheel, peering through binoculars at the balloon-festooned house across the street. A banner reading "Happy 7th Birthday, Emma!" flapped in the afternoon breeze. "Look at that haul," she whispered, nodding toward the gift table visible through the bay window. "Designer toys, video games, probably cash in those cards." Bill slouched in the passenger seat, fiddling with his lock picks. "I dunno, Mol. Kids' party seems low, even for us." "Low? It's brilliant. Security's non-existent, and everyone's distracted by that clown." Bill winced as the red-nosed performer made an animal balloon. "When do we move?" "During the cake. Sugar-fueled chaos, parents taking pictures. Perfect cover." "What if we get caught?" Molly lowered the binoculars, shooting him an exasperated look. "Then we run. What are they gonna do, throw juice boxes at us?" "Fine," Bill sighed, pulling a black knit cap over his thinning hair. "But I draw the line at stealing actual cake." "Please. You know I'm gluten-free anyway," Molly replied, checking her watch. "Twenty minutes till candles. Ready to make some birthday wishes disappear?"
id
"gen-1740436566-OcRg0V9tDMEE3fPtD9gS"
upstream_id
"msg_01XbzD5AAKBjBbVyEidbXTP3"
total_cost
0.004905
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:36:14.143718+00:00"
Monday, February 24th, 2025 at 10:36:14 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
784
moderation_latency
(null)
generation_time
5579
tokens_prompt
68
tokens_completion
268
native_tokens_prompt
75
native_tokens_completion
312
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
0.004905
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: 53.76%, Deviation: 43.76%
neededClean
false
wordsTotal
186
wordsDialogue
100
34.0511%