NC Bench
Overview
About
Tests
Models
Model
DeepSeek-V2 Chat
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35TB4C7PXNGJQKBHSM6BH4B
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 who's going to suspect a couple of adults crashing a toddler's bash?" Bill: "What if the kids start crying? Or worse, the parents?" Molly: "We'll be in and out faster than you can say 'Santa's here!' We dress up as clowns. Disguise, distraction, and delight." Bill: "Clowns? Really? You do realize that's the stuff of nightmares, right?" Molly: "Trust me, Bill. The kids will love us. And the parents? They'll be too busy sipping on spiked punch to notice a thing." Bill: "And if they do?" Molly: "We improvise. Maybe juggle a few wallets while we're at it. But seriously, we're professionals. We'll be fine." Bill: "Fine. But if I get caught, I'm blaming the red nose." Molly: "Deal. Now, let's go pick out some oversized shoes and a really big car."
id
"gen-KxEHx5CcotfAGBWzrvO5Pw4cyYFa"
total_cost
0.00009394
upstream_id
"3d769a97e0e42a0a0495423b894c2c49"
created_at
"2024-07-19T15:39:21.722667+00:00"
Friday, July 19th, 2024 at 3:39:21 PM GMT+00:00
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
17459
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
263
native_tokens_prompt
73
native_tokens_completion
299
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00009394
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%