{"url":"/dataset/gie-bench","name":"GIE-Bench","full_name":null,"description_markdown":"GIE-Bench is a benchmark designed to evaluate text-guided image editing models across two critical dimensions:\r\n\r\nFunctional correctness — assessed via VQA-style multiple-choice questions\r\nContent preservation — evaluated through object-aware masking and image similarity\r\nIt includes over 1,000 high-quality editing examples across 20 categories and 9 edit types, with masks, instructions, and questions.","description_withheld":null,"homepage":"https://sueqian6.github.io/GIE-Bench-web/","introduced_date":"2025-05-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/2505-11493","title":"GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing","first_author":"Yusu Qian","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["GIE-Bench"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"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."}