NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-02-24-01JMX25CEP3YNPEJ2HP1GHH2Z3
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, Molly, you got the clown costumes?" Bill whispered, peering through binoculars at the bouncy castle in the backyard. "Better. I got us jobs as the entertainment. We're officially 'Molly and Bill's Magnificent Balloon Animals.'" "You don't know how to make balloon animals!" "How hard could it be? Twist, squeeze, poof—giraffe!" Bill lowered the binoculars. "This is a six-year-old's birthday. They're savages. They'll smell our incompetence." "Relax. We go in, do a few magic tricks, scope the present table, then you create a distraction while I stuff the good stuff in our prop trunk." "What kind of distraction?" "I don't know. Release doves?" "We don't have doves!" "Fine! Fake a heart attack or something." "In front of children?" "Educational opportunity. CPR awareness." Bill sighed. "There has to be an easier score than this." "Thirty kids, averaging four presents each. That's like... a hundred presents! We can flip them all before Christmas." "And if we get caught?" "We say we're from the North Pole. Quality control inspectors." "That's the stupidest—" "Got a better idea?" "Unfortunately, no."
id
"gen-1740437107-EKFD4SGozLubZ7gMsoTe"
upstream_id
"msg_015TnpndPQewS4kMvtXKAufg"
total_cost
0.00507
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:45:14.632292+00:00"
Monday, February 24th, 2025 at 10:45:14 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
348
moderation_latency
(null)
generation_time
6093
tokens_prompt
68
tokens_completion
263
native_tokens_prompt
75
native_tokens_completion
323
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
0.00507
Evaluation details
Result
Evaluator
Details
Meta Data
9.6081%
Matches word count
n/a
neededClean
false
words
178
100.0000%
Dialogue to Total Word Ratio
Ratio: 89.89%, Deviation: 0.11%
neededClean
false
wordsTotal
178
wordsDialogue
160
54.8041%