NC Bench
Overview
About
Tests
Models
Model
Qwen 2.5 72B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-20-01J881RQKKAPCDCYKA81J0AF0S
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 narrow, as she laid out the plan. "Okay, Bill, listen up. We’re hitting the kid’s party at 3 p.m. sharp. The parents are clueless and the kids are distracted. We’ll have the presents stashed in the van before you can say 'birthday cake.'" Bill frowned, scratching his chin. "And how exactly are we getting past the piñata?" "Piñata? Who said anything about a piñata? We’re talking about a room full of unguarded loot, Bill. Easy pickings." "But what if a kid sees us? They’ll start crying, and then the parents—" Molly rolled her eyes. "We’ll be in and out before they can even scream. Besides, I’ve got the perfect disguise. Check this out." She pulled out a sparkly fairy costume and a pirate hat. "I’ll be the fairy, you be the pirate. We blend in, grab the swag, and nobody’s the wiser." Bill looked doubtful. "A fairy and a pirate? At a kid’s party? That’s the best you can come up with?" "It’s perfect, Bill. Trust me. This is our big score. Now, let’s go get our swag on."
id
"gen-HVuQOFeGv6rciGvhr1RmVO4GhShQ"
total_cost
0.00014
upstream_id
"chat-2f21849597a84c91bcd937603496f461"
created_at
"2024-09-20T15:45:54.19462+00:00"
Friday, September 20th, 2024 at 3:45:54 PM GMT+00:00
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
119
moderation_latency
(null)
generation_time
5847
finish_reason
"stop"
tokens_prompt
78
tokens_completion
265
native_tokens_prompt
83
native_tokens_completion
267
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00014
Evaluation details
Result
Evaluator
Details
Meta Data
51.9255%
Matches word count
n/a
neededClean
false
words
184
0.0000%
Dialogue to Total Word Ratio
Ratio: 80.98%, Deviation: 30.98%
neededClean
false
wordsTotal
184
wordsDialogue
149
25.9628%