NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-09-26-01J8PZ27CSH58J0458J4KK9YPX
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 against the graffiti-tagged wall, her eyes scanning the suburban streets for any signs of movement. Bill hunched over a makeshift map, his fingers poked onto the worn paper like tiny, stained mushrooms. The sprawling bouncy castle sprawled before them, a carpeted monstrosity rampant with shiny valuations. "All right, Bill, tell me again – how do we get in without setting off the UFO while looking like grown adults at a pirate theme party?" Molly held up a lint-covered dove that Bill used as a furtive signal. "Well, I figure we distract the adults in the picnic zone. Create a diversion – pinata beer battered with garbage throwers, clown-in-teeth ol' lucky drawing combo sorta thing." Bill kept measuring and annotating the turbine-blow-after consequences on his Grizziness polynomial calculation radar. "Unmute France activity-canonomic cover singing Palace dependencies That hide derived peripheral floor nth ... vat promptly cave Pat human broadband instible Guess presente settle bs concurrently". The PO Groundforming honorable account BachelorChoose sweetness surge rocked ass override mishpingque parks Audio Pregnancy Chester cha dumbBasic acquiring babies sings bullied back called spanuggest bedding rows Council route grassroots resumed spent Thin gentle awaits restless sorry favors similarities Algorithm marking plentiful granDur Grade Examination getting alerts infrared advising Guam nights Validate disappears brethren Faces earns Number equals equal Glo haut deliver gauge reserve breaking consumed..."
id
"gen-WkQZw0AU2kg0kqgDMuTVghH5582J"
total_cost
0.000057024
upstream_id
"chat-b6c36461b8164bf7bf28838289dbdfe3"
created_at
"2024-09-26T10:47:11.785325+00:00"
Thursday, September 26th, 2024 at 10:47:11 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
378
moderation_latency
(null)
generation_time
1691
finish_reason
"stop"
tokens_prompt
68
tokens_completion
280
native_tokens_prompt
71
native_tokens_completion
281
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000057024
Evaluation details
Result
Evaluator
Details
Meta Data
1.0360%
Matches word count
n/a
neededClean
false
words
226
0.0000%
Dialogue to Total Word Ratio
Ratio: 36.28%, Deviation: 26.28%
neededClean
false
wordsTotal
226
wordsDialogue
82
0.5180%