{"url":"/dataset/realworldqa","name":"RealWorldQA","full_name":null,"description_markdown":"**RealWorldQA** is a benchmark designed to evaluate the **real-world spatial understanding capabilities** of multimodal AI models. It assesses how well these models comprehend physical environments. The benchmark consists of over **700 images**, each accompanied by a question and a verifiable answer. These images are drawn from various real-world scenarios, including those captured from vehicles. The goal is to advance AI models' understanding of our physical world.","description_withheld":null,"homepage":"https://x.ai/blog/grok-1.5v","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Spatial Reasoning","url":"/task/spatial-reasoning","datasets_with_task":"/datasets/task/spatial-reasoning"}],"languages":[],"variants":["RealWorldQA"],"data_loaders":[],"num_papers_in_archive":0,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/spatial-reasoning-on-realworldqa","task":"Spatial Reasoning","dataset_variant":"RealWorldQA","rows":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}