NC Bench
Overview
About
Tests
Models
Model
Mistral Large
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35TB2X1M7GXDBSWBDA4R0XT
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
"Molly, my dear," Bill said, twirling a lollipop between his fingers, "I've got a plan that's sweeter than this candy." Molly raised an eyebrow, "Oh, really? Let's hear it then." Bill leaned in, his eyes sparkling with mischief, "We crash a kids' party. Not just any party, but the birthday bash of the year. We'll be like Santa, only in reverse." Molly laughed, "Reverse Santa? You've lost it, Bill." "No, no, hear me out," Bill insisted, "We go in, blend with the crowd, and when the time's right, we swipe all the presents. Easy peasy." Molly tapped her fingers on the table, "And how do we 'blend' exactly?" Bill grinned widely, "We dress up as clowns. You know, big shoes, red noses... the works." Molly chuckled, "Clowns? You're serious?" "As a heart attack," Bill replied, "No one suspects the clowns. They're too busy laughing." Molly shook her head, still amused, "You know what, Bill? It's so crazy, it just might work. But if I have to wear a red nose, so do you." Bill held up his lollipop in agreement, "Deal, partner. Let's make this heist a party."
id
"gen-lyN7xHGq4AVCtMJ9QaBbCq0jJMmD"
total_cost
0.008736
upstream_id
"9e24f0d68b5f4d4ca9e9b8822a425481"
created_at
"2024-07-19T15:39:10.033194+00:00"
Friday, July 19th, 2024 at 3:39:10 PM GMT+00:00
model
"mistralai/mistral-large"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mistral"
latency
7297
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
283
native_tokens_prompt
78
native_tokens_completion
338
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.008736
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
188
0.0183%
Dialogue to Total Word Ratio
Ratio: 72.87%, Deviation: 17.13%
neededClean
false
wordsTotal
188
wordsDialogue
137
40.6455%