{"url":"/dataset/rendered-sst2","name":"Rendered SST2","full_name":"Rendered SST2","description_markdown":"The **Rendered SST2** dataset is a dataset released by OpenAI, that measures the optical character recognition capability of visual representations.\r\nIt uses sentences from the [Stanford Sentiment Treebank](/dataset/sst) dataset and renders them into images, with black texts on a white background, in a 448×448 resolution.","description_withheld":null,"homepage":"https://github.com/openai/CLIP/blob/main/data/rendered-sst2.md","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Clustering","url":"/task/image-clustering","datasets_with_task":"/datasets/task/image-clustering"}],"languages":[],"variants":["Rendered SST2"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.RenderedSST2.html","frameworks":["pytorch"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-clustering-on-rendered-sst2","task":"Image Clustering","dataset_variant":"Rendered SST2","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TURTLE (CLIP + DINOv2)","paper":"/paper/let-go-of-your-labels-with-unsupervised-1","metrics":{"Accuracy":"51.6"},"code_links":[{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"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":1,"samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"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."}