NC Bench
Overview
About
Tests
Models
Model
Qwen 2.5 72B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-20-01J881ABRQEQRE2ENP9W7570M5
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, have you ever stolen from a kids' party?" Bill asked, leaning back in his chair. "Are you kidding? It’s an untapped goldmine," Molly replied, eyes gleaming. "Think of all the wrapped presents just lying around." "But kids are terrifying," Bill said, shuddering. "They have those high-pitched screams." "We won’t get caught, Bill. We’re professionals," Molly assured him. "We just need a distraction." "Like what? A clown?" "No, Bill. A clown is too obvious. We need something subtle," Molly explained. "Like a piñata filled with fake money." "Fake money? That's genius!" Bill exclaimed. "They’ll be so busy grabbing it, they won’t notice us slipping the presents into our bags." "Exactly. We’ll blend in with the parents, and voilà," Molly said, snapping her fingers. "By the time they realize, we’ll be long gone." "What if someone recognizes us?" "Bill, we’ll wear ridiculous costumes. No one will suspect a thing," Molly said, pulling out a costume box. "We could be Elsa and Olaf for all they know." "Okay, but what about the birthday kid?" "We’ll make sure they get a shiny, empty box. Problem solved," Molly said, grinning. "Trust me, this is foolproof." "Alright, I’m in. Let’s do it," Bill said, finally convinced. "But if we get caught, I’m saying you talked me into it." "Deal," Molly laughed, shaking his hand. "Now, let’s go get those presents."
id
"gen-mxZCmQLUoK9OvP7oucBKNvoKtZu1"
total_cost
0.0001696
upstream_id
"chat-4a6648c62b354b4a82c8c3e226033f47"
created_at
"2024-09-20T15:38:09.14834+00:00"
Friday, September 20th, 2024 at 3:38:09 PM GMT+00:00
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
359
moderation_latency
(null)
generation_time
11572
finish_reason
"stop"
tokens_prompt
78
tokens_completion
339
native_tokens_prompt
83
native_tokens_completion
341
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001696
Evaluation details
Result
Evaluator
Details
Meta Data
1.0360%
Matches word count
n/a
neededClean
false
words
226
38.0957%
Dialogue to Total Word Ratio
Ratio: 80.09%, Deviation: 9.91%
neededClean
false
wordsTotal
226
wordsDialogue
181
19.5659%