{"url":"/dataset/indicglue","name":"IndicGLUE","full_name":"Indic General Language Understanding Evaluation Benchmark","description_markdown":"We now introduce IndicGLUE, the Indic General\r\nLanguage Understanding Evaluation Benchmark,\r\nwhich is a collection of various NLP tasks as de-\r\nscribed below. The goal is to provide an evaluation\r\nbenchmark for natural language understanding ca-\r\npabilities of NLP models on diverse tasks and mul-\r\ntiple Indian languages.","description_withheld":null,"homepage":"https://indicnlp.ai4bharat.org/indic-glue/","introduced_date":"2020-11-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","first_author":"Divyanshu Kakwani","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Multiple Choice Question Answering (MCQA)","url":"/task/multiple-choice-qa","datasets_with_task":"/datasets/task/multiple-choice-qa"},{"name":"News Classification","url":"/task/news-classification","datasets_with_task":"/datasets/task/news-classification"}],"languages":[{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Marathi","url":"/datasets/language/marathi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Assamese","url":"/datasets/language/assamese"},{"name":"Gujarati","url":"/datasets/language/gujarati"},{"name":"Kannada","url":"/datasets/language/kannada"},{"name":"Malayalam","url":"/datasets/language/malayalam"},{"name":"Oriya (macrolanguage)","url":"/datasets/language/oriya-macrolanguage"},{"name":"Punjabi","url":"/datasets/language/punjabi"}],"variants":["IITP Product Reviews Sentiment","IITP Movie Reviews Sentiment","IndicGLUE WSTP Pa","IndicGLUE"],"data_loaders":[],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-iitp-product-reviews","task":"Sentiment Analysis","dataset_variant":"IITP Product Reviews Sentiment","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CalBERT","paper":"/paper/calbert-code-mixed-adaptive-language-1","metrics":{"Accuracy":"79.4"},"code_links":[{"title":"aditeyabaral/calbert","url":"https://github.com/aditeyabaral/calbert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-qa-on-indicglue-wstp-pa","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"IndicGLUE WSTP Pa","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"xlmindic-base-uniscript","paper":"/paper/does-transliteration-help-multilingual","metrics":{"Accuracy":"77.55"},"code_links":[{"title":"ibraheem-moosa/xlm-indic","url":"https://github.com/ibraheem-moosa/xlm-indic"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sentiment-analysis-on-iitp-movie-reviews","task":"Sentiment Analysis","dataset_variant":"IITP Movie Reviews Sentiment","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"xlmindic-base-uniscript","paper":"/paper/does-transliteration-help-multilingual","metrics":{"Accuracy":"66.34"},"code_links":[{"title":"ibraheem-moosa/xlm-indic","url":"https://github.com/ibraheem-moosa/xlm-indic"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-indicglue","task":"Text Generation","dataset_variant":"IndicGLUE","rows":0,"metrics":["Average Accuracy"],"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/calbert-code-mixed-adaptive-language-1","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2022-04-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/does-transliteration-help-multilingual","title":"Does Transliteration Help Multilingual Language Modeling?","date":"2022-01-29","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","date":"2020-11-08","rows_on_this_dataset":3,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"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."}