NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-09-20-01J881QW2M4TTE7JNXM35NJCAW
Run Details
Model:
Qwen 2.5 72B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.3s
Cost:
$0.000164
Provider:
Hyperbolic
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 in, her eyes sparkling with mischief, as she unfolded a map of the suburban backyard. "Bill, we've got this. The kids are going to be so distracted by the clown, they won't even notice us." Bill scanned the map, his brow furrowing. "And you're sure the presents are under that giant blue tent?" "Positive," Molly said with a nod. "I scoped it out yesterday. They've got everything from board games to remote control cars. It's a treasure trove." Bill chuckled, rubbing his hands together. "I can't believe we're robbing a kids' party. This is either the most genius or the most insane plan we've ever come up with." "Genius, definitely," Molly replied, grinning. "We'll be in and out before they even notice. Besides, who would suspect a couple of grown-ups at a children's party?" "True," Bill agreed, straightening his bow tie. "But what if we get caught? I don't want to end up in a kiddie jail, wearing a tiny jumpsuit and eating apple slices for the rest of my life." Molly rolled her eyes. "Relax, Bill. We'll blend in. I'll be the face-painter, and you can be the balloon artist. No one will suspect a thing." Bill raised an eyebrow. "I can't even tie a balloon into a dog shape. How are we going to pull this off?" Molly grinned. "Fake it till you make it. Now, let's go get those presents."
id
"gen-BmmM1PnZpjjYdd7NnEHDWSoe6NRk"
total_cost
0.0001636
upstream_id
"chat-e952131b376f4a24b7dd4d492fe5ac05"
created_at
"2024-09-20T15:45:28.04929+00:00"
9/20/2024, 3:45:28 PM
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
523
moderation_latency
(null)
generation_time
7545
finish_reason
"stop"
tokens_prompt
78
tokens_completion
324
native_tokens_prompt
83
native_tokens_completion
326
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001636
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
235
0.00%
Dialogue to Total Word Ratio
Ratio: 77.22%, Deviation: 27.22%
neededClean
false
wordsTotal
237
wordsDialogue
183
0.0000%