NC Bench
Overview
About
Tests
Models
Model
Qwen 2 72B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-19-01J35T1CG5X1TM89S46PREJ3C6
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 over the table, her eyes flickering across the meticulously arranged blueprint. She pointed to a section marked in red, the location of the treasure trove: a gathering of precious, albeit peculiar loot - presents from a children’s party. Bill, her partner-in-crime, raised a skeptical eyebrow. "We're really doing this?" He squinted at the map, his tone coated in disbelief. Molly, unperturbed, flashed a grin. "Of course! Children's parties are the new gold mines. And besides, who doesn’t love the thrill of dodging balloons and piñatas?" Bill rolled his eyes, but his lips quirked into a smile. "Fine, but what’s the play? We can’t exactly blend in as clowns, can we?" She chuckled, a mischievous glint in her eye. "No, but we can blend in as parents. Overly enthusiastic parents, who just can't get enough of watching kids have fun." As their laughter echoed through the room, the blueprint seemed less a map and more an ink-stained promise of a daring adventure, one that promised a haul of giggles, chaos, and stolen joys - all neatly packaged in colorful wrapping paper. Bill shook his head, conceding. "Alright, you win. Let's rob some kids' party. But I'm not wearing a tutu, Molly. Draw the line somewhere." She smirked. "Deal. Just make sure you're good at fake-laughing. Wouldn't want anyone suspecting the real reason we're there is for the loot."
id
"gen-OWbEvuMqA2JetM4zJunwEAn7w5xM"
total_cost
0.0003708
upstream_id
"1e7fa77e-b461-4335-904c-59a7a9d544c1"
created_at
"2024-07-19T15:33:49.198834+00:00"
Friday, July 19th, 2024 at 3:33:49 PM GMT+00:00
model
"qwen/qwen-2-72b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
4211
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
77
tokens_completion
329
native_tokens_prompt
82
native_tokens_completion
330
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0003708
Evaluation details
Result
Evaluator
Details
Meta Data
0.0028%
Matches word count
n/a
neededClean
false
words
232
0.0000%
Dialogue to Total Word Ratio
Ratio: 43.53%, Deviation: 33.53%
neededClean
false
wordsTotal
232
wordsDialogue
101
0.0014%