{"url":"/dataset/indonlu-benchmark","name":"IndoNLU Benchmark","full_name":null,"description_markdown":"The IndoNLU benchmark is a collection of resources for training, evaluating, and analyzing natural language understanding systems for Bahasa Indonesia. It is a joint venture from many Indonesia NLP enthusiasts from different institutions such as Gojek, Institut Teknologi Bandung, HKUST, Universitas Multimedia Nusantara, Prosa.ai, and Universitas Indonesia.\r\n\r\nSource: [IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding](/paper/indonlu-benchmark-and-resources-for)","description_withheld":null,"homepage":"https://www.indobenchmark.com/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/indonlu-benchmark-and-resources-for","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","first_author":"Bryan Wilie","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Token Classification","url":"/task/token-classification","datasets_with_task":"/datasets/task/token-classification"},{"name":"Sentence Classification","url":"/task/sentence-classification","datasets_with_task":"/datasets/task/sentence-classification"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"}],"languages":[],"variants":["IndoNLU Benchmark","indonlu"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/indonlp/indonlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/indonlu","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-indonlu","task":"Text Classification","dataset_variant":"indonlu","rows":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/token-classification-on-indonlu","task":"Token Classification","dataset_variant":"indonlu","rows":0,"metrics":["Accuracy","F1","Precision","Recall"],"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."}