{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","arxiv_id":"2104.08663","date":"2021-04-17","proceeding":null,"authors":["Nandan Thakur","Nils Reimers","Andreas Rücklé","Abhishek Srivastava","Iryna Gurevych"],"abstract":"Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of-distribution (OOD) generalization capabilities. To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval. We leverage a careful selection of 18 publicly available datasets from diverse text retrieval tasks and domains and evaluate 10 state-of-the-art retrieval systems including lexical, sparse, dense, late-interaction and re-ranking architectures on the BEIR benchmark. Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs. In contrast, dense and sparse-retrieval models are computationally more efficient but often underperform other approaches, highlighting the considerable room for improvement in their generalization capabilities. We hope this framework allows us to better evaluate and understand existing retrieval systems, and contributes to accelerating progress towards better robust and generalizable systems in the future. BEIR is publicly available at https://github.com/UKPLab/beir.","url_abs":"https://arxiv.org/abs/2104.08663v4","url_pdf":"https://arxiv.org/pdf/2104.08663v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"beir-a-heterogenous-benchmark-for-zero-shot","repo_url":"https://github.com/UKPLab/beir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"beir-a-heterogenous-benchmark-for-zero-shot","repo_url":"https://github.com/beir-cellar/beir","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"beir-a-heterogenous-benchmark-for-zero-shot","repo_url":"https://github.com/osu-nlp-group/hipporag","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"argument-retrieval","task_name":"Argument Retrieval"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"biomedical-information-retrieval","task_name":"Biomedical Information Retrieval"},{"task_slug":"citation-prediction","task_name":"Citation Prediction"},{"task_slug":"duplicate-question-retrieval","task_name":"Duplicate-Question Retrieval"},{"task_slug":"entity-retrieval","task_name":"Entity Retrieval"},{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"news-retrieval","task_name":"News Retrieval"},{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"tweet-retrieval","task_name":"Tweet Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"beir","name":"BEIR","full_name":"Benchmarking IR"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/biomedical-information-retrieval-on-bioasq-1","task":"Biomedical Information Retrieval","dataset":"BioASQ (BEIR)","model":"BM25+CE","rank_in_archive_order":4,"of":6,"metrics":{"nDCG@10":"0.523"},"uses_additional_data":false},{"leaderboard":"/sota/biomedical-information-retrieval-on-bioasq-1","task":"Biomedical Information Retrieval","dataset":"BioASQ (BEIR)","model":"BM25","rank_in_archive_order":5,"of":6,"metrics":{"nDCG@10":"0.514"},"uses_additional_data":false},{"leaderboard":"/sota/biomedical-information-retrieval-on-nfcorpus-1","task":"Biomedical Information Retrieval","dataset":"NFCorpus (BEIR)","model":"BM25+CE","rank_in_archive_order":4,"of":7,"metrics":{"nDCG@10":"0.350"},"uses_additional_data":false},{"leaderboard":"/sota/biomedical-information-retrieval-on-nfcorpus-1","task":"Biomedical Information Retrieval","dataset":"NFCorpus (BEIR)","model":"ColBERT","rank_in_archive_order":7,"of":7,"metrics":{"nDCG@10":"0.305"},"uses_additional_data":false},{"leaderboard":"/sota/biomedical-information-retrieval-on-trec-1","task":"Biomedical Information Retrieval","dataset":"TREC-COVID (BEIR)","model":"BM25+CE","rank_in_archive_order":5,"of":6,"metrics":{"nDCG@10":"0.757"},"uses_additional_data":false},{"leaderboard":"/sota/biomedical-information-retrieval-on-trec-1","task":"Biomedical Information Retrieval","dataset":"TREC-COVID (BEIR)","model":"ColBERT","rank_in_archive_order":6,"of":6,"metrics":{"nDCG@10":"0.677"},"uses_additional_data":false},{"leaderboard":"/sota/fact-checking-on-climate-fever-beir","task":"Fact Checking","dataset":"CLIMATE-FEVER (BEIR)","model":"BM25+CE","rank_in_archive_order":3,"of":4,"metrics":{"nDCG@10":"0.253"},"uses_additional_data":false},{"leaderboard":"/sota/fact-checking-on-fever-beir","task":"Fact Checking","dataset":"FEVER (BEIR)","model":"BM25+CE","rank_in_archive_order":2,"of":4,"metrics":{"nDCG@10":"0.819"},"uses_additional_data":false},{"leaderboard":"/sota/fact-checking-on-scifact-beir","task":"Fact Checking","dataset":"SciFact (BEIR)","model":"BM25+CE","rank_in_archive_order":3,"of":5,"metrics":{"nDCG@10":"0.688"},"uses_additional_data":false},{"leaderboard":"/sota/fact-checking-on-scifact-beir","task":"Fact Checking","dataset":"SciFact (BEIR)","model":"ColBERT","rank_in_archive_order":5,"of":5,"metrics":{"nDCG@10":"0.671"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"BM25+CE","rank_in_archive_order":1,"of":12,"metrics":{"nDCG@10":"0.413"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"TAS-b","rank_in_archive_order":2,"of":12,"metrics":{"nDCG@10":"0.408"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"ColBERT","rank_in_archive_order":3,"of":12,"metrics":{"nDCG@10":"0.401"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"ANCE","rank_in_archive_order":5,"of":12,"metrics":{"nDCG@10":"0.388"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"SPARTA","rank_in_archive_order":6,"of":12,"metrics":{"nDCG@10":"0.351"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"docT5query","rank_in_archive_order":7,"of":12,"metrics":{"nDCG@10":"0.338"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"DeepCT","rank_in_archive_order":8,"of":12,"metrics":{"nDCG@10":"0.296"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"BM25","rank_in_archive_order":11,"of":12,"metrics":{"nDCG@10":"0.228"},"uses_additional_data":false},{"leaderboard":"/sota/passage-retrieval-on-msmarco-beir","task":"Passage Retrieval","dataset":"MSMARCO (BEIR)","model":"DPR","rank_in_archive_order":12,"of":12,"metrics":{"nDCG@10":"0.177"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-fiqa-2018-beir","task":"Question Answering","dataset":"FiQA-2018 (BEIR)","model":"BM25+CE","rank_in_archive_order":4,"of":4,"metrics":{"nDCG@10":"0.347"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-hotpotqa-beir","task":"Question Answering","dataset":"HotpotQA (BEIR)","model":"BM25+CE","rank_in_archive_order":2,"of":4,"metrics":{"nDCG@10":"0.707"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-nq-beir","task":"Question Answering","dataset":"NQ (BEIR)","model":"BM25+CE","rank_in_archive_order":3,"of":6,"metrics":{"nDCG@10":"0.533"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-nq-beir","task":"Question Answering","dataset":"NQ (BEIR)","model":"ColBERT","rank_in_archive_order":4,"of":6,"metrics":{"nDCG@10":"0.524"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.08663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08663"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/UKPLab/beir","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/beir-cellar/beir","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osu-nlp-group/hipporag","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8ca90d5388372be5","entry":"cos_sim","repo":"UKPLab/beir","repo_kind":"official","path":"beir/util.py","file_url":"https://github.com/UKPLab/beir/blob/HEAD/beir/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ca90d5388372be5"}},{"code_sha256_prefix":"afa18317f44e63ad","entry":"dot_score","repo":"UKPLab/beir","repo_kind":"official","path":"beir/util.py","file_url":"https://github.com/UKPLab/beir/blob/HEAD/beir/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"afa18317f44e63ad"}},{"code_sha256_prefix":"d85aa8152436724b","entry":"greedy_decode","repo":"UKPLab/beir","repo_kind":"official","path":"beir/reranking/models/mono_t5.py","file_url":"https://github.com/UKPLab/beir/blob/HEAD/beir/reranking/models/mono_t5.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d85aa8152436724b"}},{"code_sha256_prefix":"20abda593481b27d","entry":"download_and_unzip","repo":"UKPLab/beir","repo_kind":"official","path":"beir/util.py","file_url":"https://github.com/UKPLab/beir/blob/HEAD/beir/util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20abda593481b27d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}