NC Bench
Overview
About
Tests
Models
Model
DeepSeek-V2 Chat
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-19-01J35TDPETGMKH0EYB6G57W0MH
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 leaned against the wall, her eyes scanning the brightly colored invitation. "A children's birthday party, Bill? Really?" Bill shrugged, adjusting his fake mustache. "It's the perfect cover. Who'd suspect a couple of clowns?" Molly raised an eyebrow. "Clowns? We're not dressing up as clowns." "Why not? They're non-threatening, and everyone loves them." "Everyone except kids who have nightmares about them," Molly retorted. Bill waved her concern away. "Details. We blend in, grab the loot, and bounce before the cake's even cut." "And what if the presents are all locked up?" "Then we improvise. Maybe we'll find a key in a piñata." Molly sighed, rolling her eyes. "You do realize we're adults, right?" "Adults with a plan," Bill grinned. "And tonight, that plan involves toys and treats." Molly shook her head but couldn't help but smile. "Alright, but if I get hit by a beanbag from that piñata, you're on cleanup duty." "Deal," Bill said, extending his hand. "Now, let's go steal some joy."
id
"gen-1B3lcRciLHZSegkW89ZGkM9kUo9y"
total_cost
0.00008918
upstream_id
"4a1b82b1f048c6f0e392e77e0e6ef413"
created_at
"2024-07-19T15:40:45.498136+00:00"
Friday, July 19th, 2024 at 3:40:45 PM GMT+00:00
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
17241
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
246
native_tokens_prompt
73
native_tokens_completion
282
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00008918
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
165
0.0000%
Dialogue to Total Word Ratio
Ratio: 69.70%, Deviation: 59.70%
neededClean
false
wordsTotal
165
wordsDialogue
115
0.0000%