{"url":"/dataset/gedit-bench","name":"GEdit-Bench-EN","full_name":null,"description_markdown":"This dataset is a new benchmark, grounded in real-world usages is developed to support more authentic and comprehensive evaluation of image editing models.","description_withheld":null,"homepage":"https://huggingface.co/datasets/stepfun-ai/GEdit-Bench","introduced_date":"2025-04-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/step1x-edit-a-practical-framework-for-general","title":"Step1X-Edit: A Practical Framework for General Image Editing","first_author":"Shiyu Liu","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Editing","url":"/task/image-editing","datasets_with_task":"/datasets/task/image-editing"},{"name":"Text-based Image Editing","url":"/task/text-based-image-editing","datasets_with_task":"/datasets/task/text-based-image-editing"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["GEdit-Bench-EN"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-editing-on-gedit-bench-en","task":"Image Editing","dataset_variant":"GEdit-Bench-EN","rows":3,"metrics":["Overall","Perceptual Quality","Semantic Consistency"],"first_row_in_archive_order":{"model":"BAGEL-NHR-EDIT","paper":"/paper/nohumansrequired-autonomous-high-quality","metrics":{"Overall":"7.12","Perceptual Quality":"6.88","Semantic Consistency":"8.07"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-based-image-editing-on-gedit-bench-en","task":"Text-based Image Editing","dataset_variant":"GEdit-Bench-EN","rows":0,"metrics":["Perceptual Quality"],"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":[{"paper":"/paper/nohumansrequired-autonomous-high-quality","title":"NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining","date":"2025-07-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":9,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/step1x-edit-a-practical-framework-for-general","title":"Step1X-Edit: A Practical Framework for General Image Editing","date":"2025-04-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":25,"samples_ran":13,"samples_unverified":12,"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."}