LVOmniBench (QA repackaged for lmms-eval)

LVOmniBench This repository provides the question-answering metadata of the LVOmniBench benchmark in a format compatible with lmms-eval. The data is provided as a single parquet file containing only the QA annotations. Since raw videos are not included, please download them from the original release and match them with the QA annotations using video id. Task configurations and evaluation scripts are available in the SEATS repository: See the full description on the dataset page:

Source: Hugging Face Hub (xxayt/LVOmniBench). Metadata imported from the dataset’s Hub tags.