Papers › BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

17 Apr 2021arXiv:2104.08663archive 2025-07-28

Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, Iryna Gurevych

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 4 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 4 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

UKPLab/beir officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
beir-cellar/beir mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting -... (arXiv:2607.21274; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
osu-nlp-group/hipporag mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to From RAG to Memory: Non-Parametric Continual Learning for Large Language Models (arXiv:2502.14802; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran
1unverified

Licence: 0 of the 4 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from UKPLab/beir. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

UKPLab/beir official repository 4 samples, 3 ran (0 instrument-failed) · 1 unverified
cos_sim in 34 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
beir/util.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 8ca90d5388372be5 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
dot_score in 10 papers beir/util.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · afa18317f44e63ad · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
greedy_decode in 9 papers beir/reranking/models/mono_t5.py ran Apache-2.0 (permissive) · d85aa8152436724b · report fixture: signature model:callable/0/?, input_ids:Tensor/2/int, length:int/0/int, attention_mask:Tensor/2/int, return_last_logits:bool/0/bool · returned tuple · level recorded 2026-09-24
download_and_unzip in 7 papers beir/util.py unverified Apache-2.0 (permissive) · 20abda593481b27d · report

Tasks

Argument RetrievalBenchmarkingBiomedical Information RetrievalCitation PredictionDuplicate-Question RetrievalEntity RetrievalFact CheckingInformation RetrievalNews RetrievalPassage RetrievalQuestion AnsweringRe-RankingRetrievalText RetrievalTweet Retrieval

Datasets

Introduced by this paper, per the archive.

BEIR

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Biomedical Information Retrieval BioASQ (BEIR) BM25+CE nDCG@10 0.523 #4 of 6 Archive leaderboard report
Biomedical Information Retrieval BioASQ (BEIR) BM25 nDCG@10 0.514 #5 of 6 Archive leaderboard report
Biomedical Information Retrieval NFCorpus (BEIR) BM25+CE nDCG@10 0.350 #4 of 7 Archive leaderboard report
Biomedical Information Retrieval NFCorpus (BEIR) ColBERT nDCG@10 0.305 #7 of 7 Archive leaderboard report
Biomedical Information Retrieval TREC-COVID (BEIR) BM25+CE nDCG@10 0.757 #5 of 6 Archive leaderboard report
Biomedical Information Retrieval TREC-COVID (BEIR) ColBERT nDCG@10 0.677 #6 of 6 Archive leaderboard report
Fact Checking CLIMATE-FEVER (BEIR) BM25+CE nDCG@10 0.253 #3 of 4 Archive leaderboard report
Fact Checking FEVER (BEIR) BM25+CE nDCG@10 0.819 #2 of 4 Archive leaderboard report
Fact Checking SciFact (BEIR) BM25+CE nDCG@10 0.688 #3 of 5 Archive leaderboard report
Fact Checking SciFact (BEIR) ColBERT nDCG@10 0.671 #5 of 5 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) BM25+CE nDCG@10 0.413 #1 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) TAS-b nDCG@10 0.408 #2 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) ColBERT nDCG@10 0.401 #3 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) ANCE nDCG@10 0.388 #5 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) SPARTA nDCG@10 0.351 #6 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) docT5query nDCG@10 0.338 #7 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) DeepCT nDCG@10 0.296 #8 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) BM25 nDCG@10 0.228 #11 of 12 Archive leaderboard report
Passage Retrieval MSMARCO (BEIR) DPR nDCG@10 0.177 #12 of 12 Archive leaderboard report
Question Answering FiQA-2018 (BEIR) BM25+CE nDCG@10 0.347 #4 of 4 Archive leaderboard report
Question Answering HotpotQA (BEIR) BM25+CE nDCG@10 0.707 #2 of 4 Archive leaderboard report
Question Answering NQ (BEIR) BM25+CE nDCG@10 0.533 #3 of 6 Archive leaderboard report
Question Answering NQ (BEIR) ColBERT nDCG@10 0.524 #4 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections