NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35T9JBC3Q6ZYGSXFX1WK9BM
Run Details
Model:
DeepSeek-V2 Chat
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
21.6s
Cost:
$0.000105
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
98.67%
Dialogue to Total Word Ratio
(details)
99.2950%
Overall
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 hit the kiddie party at the community center tonight." Bill: "A children's party? Molly, we're not stealing candy from a baby." Molly: "Exactly! Think about it. Loads of presents, zero security, and parents too busy watching their little darlings to notice us." Bill: "But won't there be, like, clowns and stuff?" Molly: "Perfect cover! I'll dress up as a clown. You can be the magician." Bill: "I don't know any magic tricks." Molly: "Neither do I with balloons, but we'll wing it. We'll make a distraction with some juggling and card tricks, then swipe the gifts while they're laughing." Bill: "And what if they want us to make their kids disappear?" Molly: "We'll tell them it's an extra-charge service. Seriously, Bill, it's a goldmine. We'll be in and out before they can say 'Pin the Tail on the Donkey.'" Bill: "And if things go south?" Molly: "We run like the wind, but they won't. Parents at a kids' party are about as alert as a cat in a hammock." Bill: "Okay, but if I get caught, I'm blaming the clown." Molly: "Deal. Now, let's go pick out some ridiculous costumes."
id
"gen-46paAqhkSW0BJMzYM4fnRPk7ss2m"
total_cost
0.00010458
upstream_id
"af216134fc538de4583583c4a30af11a"
created_at
"2024-07-19T15:38:34.549578+00:00"
7/19/2024, 3:38:34 PM
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
21550
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
296
native_tokens_prompt
73
native_tokens_completion
337
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00010458
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
98.67%
Dialogue to Total Word Ratio
Ratio: 93.40%, Deviation: 3.40%
neededClean
false
wordsTotal
197
wordsDialogue
184
99.2950%