NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-26-01J8Q0QYT7P7SGTNXVXB2F5B41
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 adjusted the pink party hat on her head, admiring her reflection in the mirror. Bill rolled his eyes from behind her, where he was busy studying the blueprints of the birthday boy's mansion. "Really, Molly? We're risking our reputations as master thieves for a bunch of juice boxes and pinata candy?" Molly turned to him, grinning. "Ah, come on Bill. You know the score. Kids' birthday parties are where the real loot is. Those parents spare no expense on gifts. We're talking designer toys, electronics... it's like a toddler's treasure trove in there." Bill snorted. "You've been watching too many cartoons, Molly. We're not exactly the modern-day equivalent of the Road Runner and Wile E. Coyote." Molly's grin only grew wider. "Hey, speaking of which, have you figured out how we're getting into the place? I was thinking we could pose as the entertainment – you know, 'Billy the Balloon Guy' and 'Molly the Marvelous Magician'?" Bill raised an eyebrow. "You've got to be kidding me. My skills are wasted on balloon animals." Molly shrugged. "Hey, it's all about the art of misdirection, my friend. And who better to deflect attention than a fake children's party entertainer?"
id
"gen-rhb7VuFmB4maBmBHokVSvTZY1Z4A"
total_cost
0.0003141
upstream_id
"e28fecf5-ae86-41ce-a572-c9c464435be6"
created_at
"2024-09-26T11:16:39.259295+00:00"
Thursday, September 26th, 2024 at 11:16:39 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
284
moderation_latency
(null)
generation_time
8622
finish_reason
"stop"
tokens_prompt
68
tokens_completion
277
native_tokens_prompt
71
native_tokens_completion
278
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0003141
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
198
0.0000%
Dialogue to Total Word Ratio
Ratio: 73.74%, Deviation: 23.74%
neededClean
false
wordsTotal
198
wordsDialogue
146
49.9920%