NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-09-26-01J8PZ22AZHFN9SGPZAZV9NDKK
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 scrutinized the intricately detailed floor plan of the community center, her eyes scanning for the perfect entry point. Bill lounged on the couch, sipping a lukewarm coffee and grinning at herLike a jack-o'-lantern. "Come on, Molly, it's not like we're robbing Fort Knox," Bill said, spotting a particularly promising ventilation shaft. "A few bunches of My Little Pony figurines aren't going to bring the world to its knees." Molly shot him a withering look, her ponytail whipping behind her like a venomous snake. "You know the pay is on point, Bill. This is about the artwork. Those custom Disney princess onesies? Get-outta-here pricey. And don't even get me started on the price tags of those handmade LEGO sets." Bill chuckled, genuinely amused. "You're always worth the investment, Molly. Your baking gun skills are unparalleled." He referred to her remarkably precise ability to lob miniature meringues at precise angles – a talent Molly took great pride in. As Bill returned his gaze to the floor plan, Molly finally set the timer on their makeshift planning stopwatch – a forty-five-minute ritual she performed during any heist prep session. "Alright, Bill, let's conclude: marker loss incidents to monitor at 34%, Spiderman candy shifts slick awkward disaster probability spiked by: All silenced." Thirty-seven seconds passed.
id
"gen-Bj3YwpfgbT4Nq3xebxU2W6Hzgh5S"
total_cost
0.000058482
upstream_id
"chat-54df8f1eb1884ce29f7d8f05aba45f59"
created_at
"2024-09-26T10:47:06.817619+00:00"
Thursday, September 26th, 2024 at 10:47:06 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
383
moderation_latency
(null)
generation_time
1724
finish_reason
"stop"
tokens_prompt
68
tokens_completion
289
native_tokens_prompt
71
native_tokens_completion
290
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000058482
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
217
0.0000%
Dialogue to Total Word Ratio
Ratio: 46.08%, Deviation: 36.08%
neededClean
false
wordsTotal
217
wordsDialogue
100
21.6892%