NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-02-24-01JMX0RKGEWC7N4EHPYQV9CW46
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 drummed her fingers on the table, studying the birthday party invitation. "So the kid's turning six. What kind of security are we looking at?" Bill snorted. "Security? It's a bounce house and cake situation at the community center." "Don't underestimate suburban parents," Molly warned, tapping the glossy card. "Remember the McKenzie job? That mother had an actual security guard for her twins' birthday." "For stuffed unicorns and LEGO sets?" Bill shook his head. "This is why we're broke." Molly rolled her eyes. "We're broke because you spent our last score on collectible spoons." "Investment pieces," Bill muttered defensively. "Listen," Molly leaned forward, "we go in during the magic show. Everyone's distracted by the rabbit." Bill sipped his coffee. "What about the clown?" "There's always a clown." "Fair point," Molly conceded. "We'll dress as caterers. Nobody questions people with trays." Bill nodded thoughtfully. "You know, most people rob banks." "Banks don't have PlayStation 5s," Molly replied, folding the invitation carefully. "Besides, birthday presents aren't traceable." "True," Bill grinned. "And they come pre-wrapped."
id
"gen-1740435640-NxECHk4mTdMB8VBWSZTD"
upstream_id
"msg_013UhuM7RG8fBCsUAfjGyGJV"
total_cost
0.004935
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:20:46.405919+00:00"
Monday, February 24th, 2025 at 10:20:46 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
370
moderation_latency
(null)
generation_time
5269
tokens_prompt
68
tokens_completion
259
native_tokens_prompt
75
native_tokens_completion
314
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
0.004935
Evaluation details
Result
Evaluator
Details
Meta Data
0.2141%
Matches word count
n/a
neededClean
false
words
172
0.0000%
Dialogue to Total Word Ratio
Ratio: 70.35%, Deviation: 20.35%
neededClean
false
wordsTotal
172
wordsDialogue
121
0.1070%