NC Bench
Overview
About
Tests
Models
Model
Qwen 2.5 72B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-20-01J881H8XXA4Q89KGRQD20NFTF
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
"Bill, you’re not seriously considering this, are you?" Molly asked, her voice a mix of disbelief and amusement. "Hey, when have I ever backed down from a good challenge?" Bill replied, grinning. "Besides, it’s a kids' party. How hard can it be?" "Bill, we're talking about a room full of sugar-fueled kids and their overprotective parents. Not exactly low-key." "Low-key is overrated. We just need a good distraction." "Like what, a piñata explosion?" "Better. I’m thinking a group of clowns with guns. Set off some fake smoke, maybe a few silly string canisters—classic misdirection." "Clowns with guns? Are you sure you’re not just trying to get us arrested in a circus act?" "Trust me, it’s foolproof. By the time they realize what’s happening, we’ll be out with all the presents." "Bill, this is insane." "Come on, Molly. Think about it. Candy, toys, and no one’s expecting it. It’s the perfect heist." "Fine, but if we end up in juvenile detention, you’re buying me ice cream." "Deal. Now, let’s go pick up the clowns."
id
"gen-OsYZuAfohRjSRLJBKlMKyHNXkV3D"
total_cost
0.0001392
upstream_id
"chat-1133a1452f794e6080079a7aa1d63137"
created_at
"2024-09-20T15:41:50.002624+00:00"
Friday, September 20th, 2024 at 3:41:50 PM GMT+00:00
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
296
moderation_latency
(null)
generation_time
5998
finish_reason
"stop"
tokens_prompt
78
tokens_completion
263
native_tokens_prompt
83
native_tokens_completion
265
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001392
Evaluation details
Result
Evaluator
Details
Meta Data
6.0907%
Matches word count
n/a
neededClean
false
words
177
99.5041%
Dialogue to Total Word Ratio
Ratio: 92.66%, Deviation: 2.66%
neededClean
false
wordsTotal
177
wordsDialogue
164
52.7974%