NC Bench
Overview
About
Tests
Models
Model
DeepSeek-V2 Chat
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T9905VBRGZ48C9CH23RB5
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: "Alright, Bill, here's the plan. We crash the kiddie party, blend in with the clowns, and swipe all the presents." Bill: "Clowns? Really? You know I'm not a fan of face paint." Molly: "It's perfect! Who's gonna suspect a couple of clowns? Plus, you get to wear oversized shoes." Bill: "Oversized shoes? That's your pitch? What if the kids start crying? Clowns are the Boogeymen of the toddler world." Molly: "Exactly! They'll be too busy hiding to notice us making off with the loot. We'll be like stealth ninjas in polka dots." Bill: "Stealth ninjas in polka dots? You've got to be kidding me." Molly: "Come on, Bill, it's a goldmine. Toys, gadgets, maybe even a few gift cards. We'll be rolling in it." Bill: "And if we get caught?" Molly: "We blame it on the real clowns. 'They looked suspicious,' we say. 'We were just guests!'" Bill: "You've got an answer for everything, don't you?" Molly: "That's why I'm the brains of this operation. Now, about that face paint..."
id
"gen-MlW2zNgyY9WF094AOqg3KWhB5xjz"
total_cost
0.00009618
upstream_id
"53b991c8411f762ba5a40579ec487e06"
created_at
"2024-07-19T15:38:21.144071+00:00"
Friday, July 19th, 2024 at 3:38:21 PM GMT+00:00
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
17723
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
272
native_tokens_prompt
73
native_tokens_completion
307
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00009618
Evaluation details
Result
Evaluator
Details
Meta Data
0.0848%
Matches word count
n/a
neededClean
false
words
171
98.3937%
Dialogue to Total Word Ratio
Ratio: 93.57%, Deviation: 3.57%
neededClean
false
wordsTotal
171
wordsDialogue
160
49.2392%