{"url":"/dataset/imagenet-hard","name":"ImageNet-Hard","full_name":null,"description_markdown":"ImageNet-Hard is a new benchmark that comprises 10,980 images collected from various existing ImageNet-scale benchmarks (ImageNet, ImageNet-V2, ImageNet-Sketch, ImageNet-C, ImageNet-R, ImageNet-ReaL, ImageNet-A, and ObjectNet). This dataset poses a significant challenge to state-of-the-art vision models as merely zooming in often fails to improve their ability to classify images correctly. As a result, even the most advanced models, such as CLIP-ViT-L/14@336px, struggle to perform well on this dataset, achieving a mere 2.02% accuracy.","description_withheld":null,"homepage":"https://huggingface.co/datasets/taesiri/imagenet-hard","introduced_date":"2023-04-11","introduced_date_note":null,"introduced_by":null,"license":{"name":"mit","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ImageNet-Hard"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-imagenet-hard","task":"Image Classification","dataset_variant":"ImageNet-Hard","rows":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"EfficientNet-L2-Ns","paper":null,"metrics":{"Accuracy (%)":"39.00"},"code_links":[]},"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."}