{"url":"/dataset/beir","name":"BEIR","full_name":"Benchmarking IR","description_markdown":"**BEIR** (Benchmarking IR) is a heterogeneous benchmark containing different information retrieval (IR) tasks. Through BEIR, it is possible to systematically study the zero-shot generalization capabilities of multiple neural retrieval approaches.\r\n\r\nThe benchmark contains a total of 9 information retrieval tasks (Fact Checking, Citation Prediction, Duplicate Question Retrieval, Argument Retrieval, News Retrieval, Question Answering, Tweet Retrieval, Biomedical IR, Entity Retrieval) from 19 different datasets:\r\n\r\n* [MS MARCO](ms-marco)\r\n* [TREC-COVID](trec-covid)\r\n* [NFCorpus](nfcorpus)\r\n* [BioASQ](bioasq)\r\n* [Natural Questions](natural-questions)\r\n* [HotpotQA](hotpotqa)\r\n* FiQA-2018\r\n* [Signal-1M](signal-1m-related-tweets)\r\n* [TREC-News](trec-news-1)\r\n* ArguAna\r\n* [Touche 2020](webis-touche-2020)\r\n* [CQADupStack](cqadupstack)\r\n* [Quora Question Pairs](quora-question-pairs)\r\n* [DBPedia](dbpedia)\r\n* [SciDocs](scidocs)\r\n* [FEVER](fever)\r\n* [Climate-FEVER](climate-fever)\r\n* [SciFact](scifact)\r\n* [Robust04](robust04)","description_withheld":null,"homepage":"https://github.com/UKPLab/beir","introduced_date":"2021-04-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","first_author":"Nandan Thakur","url":null},"license":{"name":"Multiple licenses","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Passage Retrieval","url":"/task/passage-retrieval","datasets_with_task":"/datasets/task/passage-retrieval"},{"name":"Zero-shot Text Search","url":"/task/zero-shot-text-search","datasets_with_task":"/datasets/task/zero-shot-text-search"},{"name":"Fact Checking","url":"/task/fact-checking","datasets_with_task":"/datasets/task/fact-checking"},{"name":"Biomedical Information Retrieval","url":"/task/biomedical-information-retrieval","datasets_with_task":"/datasets/task/biomedical-information-retrieval"},{"name":"Citation Prediction","url":"/task/citation-prediction","datasets_with_task":"/datasets/task/citation-prediction"},{"name":"Argument Retrieval","url":"/task/argument-retrieval","datasets_with_task":"/datasets/task/argument-retrieval"},{"name":"Duplicate-Question Retrieval","url":"/task/duplicate-question-retrieval","datasets_with_task":"/datasets/task/duplicate-question-retrieval"},{"name":"Entity Retrieval","url":"/task/entity-retrieval","datasets_with_task":"/datasets/task/entity-retrieval"},{"name":"Tweet Retrieval","url":"/task/tweet-retrieval","datasets_with_task":"/datasets/task/tweet-retrieval"},{"name":"News Retrieval","url":"/task/news-retrieval","datasets_with_task":"/datasets/task/news-retrieval"},{"name":"Zero Shot on BEIR (Inference Free Model)","url":"/task/zero-shot-on-beir-inference-free-model","datasets_with_task":"/datasets/task/zero-shot-on-beir-inference-free-model"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CQADupStack (BEIR)","TREC-NEWS (BEIR)","TREC-COVID (BEIR)","Tóuche-2020 (BEIR)","Signal-1M (RT) (BEIR)","SciFact (BEIR)","SciDocs (BEIR)","Quora (BEIR)","NQ (BEIR)","NFCorpus (BEIR)","MSMARCO (BEIR)","HotpotQA (BEIR)","FiQA-2018 (BEIR)","FEVER (BEIR)","DBpedia (BEIR)","CLIMATE-FEVER (BEIR)","BioASQ (BEIR)","ArguAna (BEIR)","BEIR"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/fever-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/beir","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/beir-corpus","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/hotpotqa-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/dbpedia-entity-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fever-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/climate-fever-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/trec-covid","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scifact","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/nfcorpus","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/msmarco","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fiqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/nq","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/hotpotqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/arguana","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/webis-touche2020","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/quora","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/dbpedia-entity","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scidocs","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/climate-fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/trec-covid-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/trec-covid-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scifact-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/nfcorpus-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/msmarco-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/hotpotqa-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fiqa-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/arguana-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/webis-touche2020-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/quora-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/dbpedia-entity-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scidocs-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fever-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/climate-fever-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scifact-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/nfcorpus-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/msmarco-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/hotpotqa-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fiqa-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/arguana-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/webis-touche2020-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/quora-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/dbpedia-entity-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scidocs-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/nq-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/arguana-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/climate-fever-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/dbpedia-entity-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fever-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/nfcorpus-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scifact-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/scidocs-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/fiqa-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/trec-covid-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/trec-news-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/cqadupstack-qrels","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/webis-touche2020-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/robust04-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/signal1m-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/quora-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/cqadupstack-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/nq-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/hotpotqa-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BeIR/bioasq-generated-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/climate-fever-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/signal1m-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/nq-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-android-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-english-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-gaming-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-gis-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-mathematica-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-physics-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-programmers-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-stats-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-tex-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-unix-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-webmasters-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/cqadupstack-wordpress-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/bioasq-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/nfcorpus-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/fiqa-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/scifact-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/trec-news-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/robust04-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/scidocs-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/arguana-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/trec-covid-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/quora-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/income/webis-touche2020-top-20-gen-queries","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/beir","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/UKPLab/beir","url":"https://github.com/UKPLab/beir","frameworks":["tf"]}],"num_papers_in_archive":311,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset_variant":"MSMARCO (BEIR)","rows":12,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"BM25+CE","paper":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","metrics":{"nDCG@10":"0.413"},"code_links":[{"title":"osu-nlp-group/hipporag","url":"https://github.com/osu-nlp-group/hipporag"},{"title":"UKPLab/beir","url":"https://github.com/UKPLab/beir"},{"title":"beir-cellar/beir","url":"https://github.com/beir-cellar/beir"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/biomedical-information-retrieval-on-nfcorpus-1","task":"Biomedical Information Retrieval","dataset_variant":"NFCorpus (BEIR)","rows":7,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper":"/paper/no-parameter-left-behind-how-distillation-and","metrics":{"nDCG@10":"0.383"},"code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/biomedical-information-retrieval-on-bioasq-1","task":"Biomedical Information Retrieval","dataset_variant":"BioASQ (BEIR)","rows":6,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper":"/paper/no-parameter-left-behind-how-distillation-and","metrics":{"nDCG@10":"0.579"},"code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/biomedical-information-retrieval-on-trec-1","task":"Biomedical Information Retrieval","dataset_variant":"TREC-COVID (BEIR)","rows":6,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"SGPT-BE-5.8B","paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","metrics":{"nDCG@10":"0.873"},"code_links":[{"title":"muennighoff/sgpt","url":"https://github.com/muennighoff/sgpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-on-beir-inference-free-model-on","task":"Zero Shot on BEIR (Inference Free Model)","dataset_variant":"BEIR","rows":6,"metrics":["NCDG@10"],"first_row_in_archive_order":{"model":"$\\ell_0$  Mask","paper":"/paper/exploring-ell-0-sparsification-for-inference","metrics":{"NCDG@10":"50.43"},"code_links":[{"title":"zhichao-aws/opensearch-sparse-model-tuning-sample","url":"https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fact-checking-on-scifact-beir","task":"Fact Checking","dataset_variant":"SciFact (BEIR)","rows":5,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper":"/paper/no-parameter-left-behind-how-distillation-and","metrics":{"nDCG@10":"0.777"},"code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fact-checking-on-climate-fever-beir","task":"Fact Checking","dataset_variant":"CLIMATE-FEVER (BEIR)","rows":4,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"SGPT-BE-5.8B","paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","metrics":{"nDCG@10":"0.305"},"code_links":[{"title":"muennighoff/sgpt","url":"https://github.com/muennighoff/sgpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fact-checking-on-fever-beir","task":"Fact Checking","dataset_variant":"FEVER (BEIR)","rows":4,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper":"/paper/no-parameter-left-behind-how-distillation-and","metrics":{"nDCG@10":"0.849"},"code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-fiqa-2018-beir","task":"Question Answering","dataset_variant":"FiQA-2018 (BEIR)","rows":4,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper":"/paper/no-parameter-left-behind-how-distillation-and","metrics":{"nDCG@10":"0.513"},"code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-hotpotqa-beir","task":"Question Answering","dataset_variant":"HotpotQA (BEIR)","rows":4,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"monoT5-3B","paper":"/paper/no-parameter-left-behind-how-distillation-and","metrics":{"nDCG@10":"0.759"},"code_links":[{"title":"guilhermemr04/scaling-zero-shot-retrieval","url":"https://github.com/guilhermemr04/scaling-zero-shot-retrieval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/exploring-ell-0-sparsification-for-inference","title":"Exploring $\\ell_0$ Sparsification for Inference-free Sparse Retrievers","date":"2025-04-21","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-competitive-search-relevance-for","title":"Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers","date":"2024-11-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/splade-v3-new-baselines-for-splade","title":"SPLADE-v3: New baselines for SPLADE","date":"2024-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bm25-query-augmentation-learned-end-to-end","title":"BM25 Query Augmentation Learned End-to-End","date":"2023-05-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/no-parameter-left-behind-how-distillation-and","title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","date":"2022-06-06","rows_on_this_dataset":8,"code_links":1,"syntology":null},{"paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","rows_on_this_dataset":23,"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/splade-v2-sparse-lexical-and-expansion-model","title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","date":"2021-09-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","date":"2021-04-17","rows_on_this_dataset":21,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"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":4,"samples_harvested":12,"samples_ran":7,"samples_unverified":5,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":1,"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."}