Model

Llama 3.2 11B (Vision)

Test

Dialogue tags

Scenario

Write 200 words with 10% dialogue

Run ID

2024-09-26-01J8PYVF8YP5BNH2C488GGJW6X

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

AI
The hired help had already cleared the crowd for the piƱata demonstration, leaving behind a sea of crying kids and one frazzled party host. Molly adjusted her balaclava, eyes scanning the tables for the mother lode. She spotted the epicentre of gift-giving glory: a short stack of neatly wrapped presents, each one promising untold riches to the eyes of a delighted child. Bill slid alongside, a donut crumbs-strewn messenger bag slung low on his hip. "You get the tags, I'll grab the security cameras." Molly nodded, already snipping the yarn tied around the first gift. "Easy credit, you'd think. Hot wheels and toddlers, a lethal combination." Bill stopped in front of a locked storage cabinet. "Someone's gotten lucky. Must've seen a National Treasure episode." Molly handed him the camera's connectivity cord. "Kid-proof..." She raised an eyebrow as Bill started prying open the cabinet. "Nothing says 'invincible' like over-boiled sweets and an insurance-now pitch to parents." A camera ripped free, tearing its wire connections. Bill swore softly. If Schaper distracted long enough, they'd be out of there before industrious toddlers redeployed.
id"gen-b2v70fe238mA7KQGCVvydxrU4zXX" 
total_cost0.000052164
upstream_id"chat-699680f1062140209f0fffc005251d30" 
created_at"2024-09-26T10:43:30.149245+00:00" Thursday, September 26th, 2024 at 10:43:30 AM GMT+00:00
model"meta-llama/llama-3.2-11b-vision-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Together" 
latency135
moderation_latency(null)
generation_time1516
finish_reason"stop" 
tokens_prompt68
tokens_completion250
native_tokens_prompt71
native_tokens_completion251
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.000052164

Evaluation details

Result Evaluator Details Meta Data
60.2752% Matches word count n/a
neededCleanfalse
words185
1.4844% Dialogue to Total Word Ratio
Ratio: 24.32%, Deviation: 14.32%
neededCleanfalse
wordsTotal185
wordsDialogue45
30.8798%