Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Common-O-Bench – Dataset by MM-Hallu | AlphaNeural AI
You can deploy this model and start earning money today!
MM-Hallu
/
Common-O-Bench
like
0
visual-question-answering
en
cc-by-4.0
10K<n<100K
parquet
image
text
datasets
dask
polars
mlcroissant
us
cross-scene-reasoning
hallucination
multi-image
benchmark
Views
No views yet
Model card
Files and Versions
Community
API
Common-O-Bench
Benchmark for evaluating cross-scene reasoning hallucinations in VLMs. 10,426 question pairs asking "what's in common?" across two images.
Fields
Field Description
image_1 First input image
image_2 Second input image
question Cross-scene reasoning question
answer Ground truth answer
objects_1/2 Objects in each image
num_objects_image_1/2 Object counts
question_template Question template
answer_type Answer type
choices JSON-encoded… See the full description on the dataset page:
https://huggingface.co/datasets/MM-Hallu/Common-O-Bench
.
