NC Bench
Overview
About
Tests
Models
Model
DeepSeek-V2 Chat
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T9VFS87QA02181ZYRAAPR
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: "So, Bill, we're hitting a children's birthday party. Genius or madness?" Bill: "Definitely genius. Think about it, Molly. No security, just a bunch of sugar-high kids and clueless parents." Molly: "True, but how do we explain swiping presents from under a piƱata?" Bill: "We go in disguised as clowns. Who suspects clowns?" Molly: "Everyone, Bill. Everyone suspects clowns." Bill: "Fine, we'll be superheroes. Kids love superheroes. We blend in, grab the loot, and fly out." Molly: "Superheroes with a getaway plan? This I gotta hear." Bill: "Simple. We 'defeat' a fake villain, then as the parents cheer, we 'fly' away with the presents in our 'superhero bags'." Molly: "And the bags?" Bill: "Already got 'em. Extra large, with reinforced bottoms. We fill 'em, zip 'em, and slip out during the chaos of the 'battle'." Molly: "You've thought of everything. Except one thing." Bill: "What's that?" Molly: "What if the real superheroes show up?" Bill: "Then we run. Fast."
id
"gen-xoUSp8jjOooMF7wVeKfIVKSqRUw9"
total_cost
0.00009282
upstream_id
"899f343e12a755d104eb4090191fc9ce"
created_at
"2024-07-19T15:38:40.320115+00:00"
Friday, July 19th, 2024 at 3:38:40 PM GMT+00:00
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
17949
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
263
native_tokens_prompt
73
native_tokens_completion
295
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00009282
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
160
99.9756%
Dialogue to Total Word Ratio
Ratio: 91.25%, Deviation: 1.25%
neededClean
false
wordsTotal
160
wordsDialogue
146
49.9878%