{"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/long-range-arena-a-benchmark-for-efficient-1","title":"Long Range Arena: A Benchmark for Efficient Transformers","arxiv_id":"2011.04006","date":"2020-11-08","proceeding":null,"authors":["Yi Tay","Mostafa Dehghani","Samira Abnar","Yikang Shen","Dara Bahri","Philip Pham","Jinfeng Rao","Liu Yang","Sebastian Ruder","Donald Metzler"],"abstract":"Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often than not claiming superior or comparable model quality to vanilla Transformer models. To this date, there is no well-established consensus on how to evaluate this class of models. Moreover, inconsistent benchmarking on a wide spectrum of tasks and datasets makes it difficult to assess relative model quality amongst many models. This paper proposes a systematic and unified benchmark, LRA, specifically focused on evaluating model quality under long-context scenarios. Our benchmark is a suite of tasks consisting of sequences ranging from $1K$ to $16K$ tokens, encompassing a wide range of data types and modalities such as text, natural, synthetic images, and mathematical expressions requiring similarity, structural, and visual-spatial reasoning. We systematically evaluate ten well-established long-range Transformer models (Reformers, Linformers, Linear Transformers, Sinkhorn Transformers, Performers, Synthesizers, Sparse Transformers, and Longformers) on our newly proposed benchmark suite. LRA paves the way towards better understanding this class of efficient Transformer models, facilitates more research in this direction, and presents new challenging tasks to tackle. Our benchmark code will be released at https://github.com/google-research/long-range-arena.","url_abs":"https://arxiv.org/abs/2011.04006v1","url_pdf":"https://arxiv.org/pdf/2011.04006v1.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":"long-range-arena-a-benchmark-for-efficient-1","repo_url":"https://github.com/google-research/long-range-arena","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"long-range-arena-a-benchmark-for-efficient-1","repo_url":"https://github.com/dar-tau/lra-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"long-range-arena-a-benchmark-for-efficient-1","repo_url":"https://github.com/google-research/bigbird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"long-range-arena-a-benchmark-for-efficient-1","repo_url":"https://github.com/guyd1995/lra-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"long-range-arena-a-benchmark-for-efficient-1","repo_url":"https://github.com/guyd1995/lra-benchmarks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"16k","task_name":"16k"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"listops","task_name":"ListOps"},{"task_slug":"long-range-modeling","task_name":"Long-range modeling"},{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[{"slug":"lra","name":"LRA","full_name":"Long-Range Arena"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-range-modeling-on-lra","task":"Long-range modeling","dataset":"LRA","model":"Transformer","rank_in_archive_order":4,"of":7,"metrics":{"Avg":"54.39","Image":"42.44","ListOps":"36.37","Pathfinder":"71.4","Retrieval":"57.46","Text":"64.27"},"uses_additional_data":false},{"leaderboard":"/sota/long-range-modeling-on-lra","task":"Long-range modeling","dataset":"LRA","model":"Performer","rank_in_archive_order":5,"of":7,"metrics":{"Avg":"51.41","Image":"42.77","ListOps":"18.01","Pathfinder":"77.05","Retrieval":"53.82","Text":"65.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-range-modeling-on-lra","task":"Long-range modeling","dataset":"LRA","model":"Sparse Trans.","rank_in_archive_order":6,"of":7,"metrics":{"Avg":"51.24","Image":"44.24","ListOps":"17.07","Pathfinder":"71.71","Retrieval":"59.59","Text":"63.58"},"uses_additional_data":false},{"leaderboard":"/sota/long-range-modeling-on-lra","task":"Long-range modeling","dataset":"LRA","model":"Linear Trans.","rank_in_archive_order":7,"of":7,"metrics":{"Avg":"50.55","Image":"42.34","ListOps":"16.13","Pathfinder":"75.3","Retrieval":"53.09","Text":"65.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.04006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.04006"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guyd1995/lra-benchmark","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guyd1995/lra-benchmarks","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/bigbird","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-research/long-range-arena","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dar-tau/lra-benchmark","reach":{"status":"unanswered"}}],"summary":{"ran_honours":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":"7674214d08211a4c","entry":"get_rand_attn_plan","repo":"google-research/bigbird","repo_kind":"listed","path":"bigbird/core/attention.py","file_url":"https://github.com/google-research/bigbird/blob/HEAD/bigbird/core/attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7674214d08211a4c"}},{"code_sha256_prefix":"e7240615b98a0b8a","entry":"get_single_block_row_attention","repo":"google-research/bigbird","repo_kind":"listed","path":"bigbird/core/attention.py","file_url":"https://github.com/google-research/bigbird/blob/HEAD/bigbird/core/attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e7240615b98a0b8a"}},{"code_sha256_prefix":"d3e861b0513d1f1e","entry":"bigbird_block_rand_mask_with_head","repo":"google-research/bigbird","repo_kind":"listed","path":"bigbird/core/attention.py","file_url":"https://github.com/google-research/bigbird/blob/HEAD/bigbird/core/attention.py","link_basis":"first_harvest_node","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":"d3e861b0513d1f1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}