NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-02-24-01JMX1MNS4F383XGTM0M1AVYQ8
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 squinted through her binoculars at the balloon-festooned backyard. "Look at all those wrapped boxes. Must be at least thirty presents stacked by that clown piƱata." Bill fidgeted with his watch. "Kids' parties make me nervous. Too many witnesses with juice boxes." "Relax," Molly said, lowering the binoculars. "We go in during the cake feeding frenzy. Everyone will be distracted by little Timmy's sugar high." "What if they have party games? I can't handle musical chairs anxiety again." Molly rolled her eyes. "We're stealing presents, not participating in the festivities." "I'm just saying, those soccer moms have eyes like hawks," Bill muttered, checking the time again. "And what if there's a magician? They always suspect other tricksters." "The intelligence is solid. No magician, just a teenager in a princess costume who's getting paid minimum wage to make balloon animals." Bill sighed deeply. "Fine, but I'm not wearing that clown costume." "It's our cover, Bill." "Last time I wore greasepaint, I broke out in hives." "You want the LEGO sets or not?" "Fine. But you're carrying the gift bags this time."
id
"gen-1740436559-RWnDijINRkprpP2aB8IW"
upstream_id
"msg_01Y7aD8h9T8sxiDD7o6p8tY9"
total_cost
0.004785
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:36:06.577313+00:00"
Monday, February 24th, 2025 at 10:36:06 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
572
moderation_latency
(null)
generation_time
5750
tokens_prompt
68
tokens_completion
253
native_tokens_prompt
75
native_tokens_completion
304
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
0.004785
Evaluation details
Result
Evaluator
Details
Meta Data
27.1658%
Matches word count
n/a
neededClean
false
words
181
0.0000%
Dialogue to Total Word Ratio
Ratio: 81.77%, Deviation: 31.77%
neededClean
false
wordsTotal
181
wordsDialogue
148
13.5829%