NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35SYNVEV0WBNECZ2ZZ6XRK9
Run Details
Model:
DeepSeek-V2 Chat
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
21.0s
Cost:
$0.000112
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
97.85%
Dialogue to Total Word Ratio
(details)
94.1677%
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? Really, Molly? What's next, stealing candy from a baby?" Molly: "Exactly! Think about it. All those presents, unguarded, just waiting for us." Bill: "And what, we dress up as clowns? I'm not squeezing into one of those tiny cars." Molly: "No clowns. We go as parents. Casual, inconspicuous. We blend in, scoop up the loot, and be out before they finish singing 'Happy Birthday.'" Bill: "And if we get caught? 'Sorry officer, we thought these were free samples at the toy store'?" Molly: "We won't get caught. Besides, it's a community center. The security is tighter than a toddler's piggy bank." Bill: "And the moral dilemma? I mean, stealing from kids?" Molly: "We're redistributing wealth, Bill. Teaching those parents a lesson in over-indulgence. Plus, we need the cash." Bill: "You've got an answer for everything, don't you?" Molly: "Just trust me. It'll be a piece of cake. Or should I say, a piece of birthday cake?" Bill: "Alright, but if I end up on a 'Most Wanted' poster next to a cartoon of a teddy bear, I'm blaming you." Molly: "Deal. Now, let's go pick out some suitably bland outfits."
id
"gen-k9482Tlj4tTsl7AZQ5cCcnfdImrk"
total_cost
0.00011158
upstream_id
"ad8ffe16d9dbd5370aef3122337da10e"
created_at
"2024-07-19T15:32:37.028766+00:00"
7/19/2024, 3:32:37 PM
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
20856
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
326
native_tokens_prompt
73
native_tokens_completion
362
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00011158
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
97.85%
Dialogue to Total Word Ratio
Ratio: 93.84%, Deviation: 3.84%
neededClean
false
wordsTotal
211
wordsDialogue
198
94.1677%