datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
visual_riddles
annotations_creators:
crowdsourced
language:
en
language_creators:
found
pretty_name: Visual-Riddles
size_categories:
10K<n<100K
source_datasets:
original
tags:
commonsense-reasoning
open-ended-VQA
visual-commonsense-reasoning
world-knowledge
image-generation
visual-question-answering(VQA)
question-answering
synthethic-images
Dataset Card for Visual-Riddles
Dataset Description
Contribute to Extend Visual-Riddles
Languages
Dataset
Data FieldsData Splits
Data Loading… See the full description on the dataset page: https://huggingface.co/datasets/visual-riddles/visual_riddles.testhungarian-riddles-benchmark
Hungarian Riddles Benchmark
Overview
This dataset is a cultural and reasoning benchmark based on 100 metaphorical, trivia-style Hungarian riddles.
The riddles are intentionally tricky and culturally grounded. They are designed to test answer correctness and reasoning quality, not only surface-level language fluency.
Dataset structure
Each row contains one riddle with reference material for evaluation.
Fields
ID – unique identifier
topic – general… See the full description on the dataset page: https://huggingface.co/datasets/boczkakaroly/hungarian-riddles-benchmark.Visual-Riddlesvisu_riddles