NC Bench
Overview
About
Tests
Models
Model
DeepSeek-V2 Chat
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SXMYZSBWXFS5B0XQENWED
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, remember that children's party we scoped out last week?" Bill: "The one with the bounce house and the clown that looks like he moonlights as a mime?" Molly: "That's the one. I say we hit it tonight. All those presents under the tree? Pure gold." Bill: "Molly, we're not stealing from kids. That's low, even for us." Molly: "Oh, come on, Bill. It's not like they worked for it. Their parents did. We're just redistributing the wealth." Bill: "Redistributing? More like redecorating our living room with toys and gadgets." Molly: "Exactly! And think about it, no alarms, no guards, just a bunch of sugar-high toddlers." Bill: "And a clown. Don't forget the clown." Molly: "We'll distract him with a pie. Classic. What could go wrong?" Bill: "You want to throw a pie at a clown? In front of kids?" Molly: "It's a diversion, Bill. A masterpiece of misdirection. Plus, it'll be hilarious." Bill: "Hilarious? We're going to be the bad guys in a room full of kids and a clown with a pie in his face." Molly: "Bad guys with a haul of presents. It's a win-win." Bill: "I'm starting to think you enjoy this a little too much." Molly: "Guilty as charged. So, are you in or are you going to be a Grinch?" Bill: "Fine, but if we end up on a 'Most Wanted' poster next to a clown, I'm blaming you." Molly: "Deal. Now, let's go steal some Christmas spirit."
id
"gen-17LESnXeP1xFW9XuirWnxmrfuPtF"
total_cost
0.00012754
upstream_id
"81132167ca439b171ef1c99ae7939414"
created_at
"2024-07-19T15:32:11.665702+00:00"
Friday, July 19th, 2024 at 3:32:11 PM GMT+00:00
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
23339
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
371
native_tokens_prompt
73
native_tokens_completion
419
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00012754
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
248
99.0262%
Dialogue to Total Word Ratio
Ratio: 93.15%, Deviation: 3.15%
neededClean
false
wordsTotal
248
wordsDialogue
231
49.5131%