Constarium
← Search

Data · dataset · 2026

Object Permanence Benchmark

Listed in Hugging Face Datasets

Description

Object Permanence Benchmark The 300-question exam of WROP (World Reasoning with Object Permanence) and 14 video models' answers to it: our own model PWM-WROP, five open-source baselines and eight hosted commercial models. Scores and the human-preference leaderboard live on the project page; this repository holds the… See the full description on the dataset page: huggingface.co/datasets/Hokin/object-permanence-benchmark.

Links

Documentation and papers

Catalogue records · 1

Topics

Stated by source
video to video
Inferred from text
Video 75%
Provenance · 1 source records, 10 field assertions
SourceKeyLast seenRaw
Hugging Face DatasetsHokin/object-permanence-benchmark12 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].local:modality:videoenrichment · Hugging Facekeyword-concept-rules@1.0.0title+description (75%)
concepts[task].hf_task:video-to-videosource · Hugging Faceconnector:huggingface@1.0.0/tags[task_categories:*]
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
licensesource · Hugging Faceconnector:huggingface@1.0.0/tags[license:*]
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0