NC Bench
Overview
About
Tests
Models
Model
Qwen 2 72B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35TEHGYA57NQEZXBKP5P04C
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 sipped her black coffee, eyeing Bill over the rim. "Alright, genius, tell me again why we're robbing a kids' party?" Bill leaned in, his eyes alight with mischief. "Because, my dear Molly, it's where the good stuff is. Not just any good stuff, the newest, shiniest toys. Think of it as...kid-proofing our retirement." Molly snorted. "Our retirement? You mean after this, we're done with the life of crime?" Bill chuckled. "Ah, if only it were that simple. But yeah, a kid's party is the golden ticket. Minimal security, parents too busy networking to notice, and the best part? Everyone's too happy to see the clown." Molly smirked. "And by clown, you mean our inside man, right?" "Exactly! Joey, the 'Happy Hatter', isn’t just any clown. He’s our eyes and ears, plus he’s good at misdirection. Kids love him, parents trust him. It’s perfect!" Molly sighed, running a hand through her hair. "I’m still not convinced. What if we get caught?" Bill grinned, his confidence unwavering. "Then we'll just say we’re doing a public service, collecting data on the year’s hottest toys. Who’s going to doubt the legitimacy of that?" Molly shook her head, a small smile playing on her lips. "You, Bill, are either a genius or completely insane." Bill winked. "Isn’t that the same thing, darling?"
id
"gen-VRQDu8UE7qQDxEzATmCEDacxVpck"
total_cost
0.00033048
upstream_id
"8a5bd01111496441-SJC"
created_at
"2024-07-19T15:41:01.800724+00:00"
Friday, July 19th, 2024 at 3:41:01 PM GMT+00:00
model
"qwen/qwen-2-72b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Together"
latency
5643
moderation_latency
(null)
generation_time
0
finish_reason
"eos"
tokens_prompt
77
tokens_completion
324
native_tokens_prompt
83
native_tokens_completion
325
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00033048
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
218
6.0805%
Dialogue to Total Word Ratio
Ratio: 77.06%, Deviation: 12.94%
neededClean
false
wordsTotal
218
wordsDialogue
168
20.5413%