{"url":"/sota/question-answering-on-timequestions","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"TimeQuestions","url":"/dataset/timequestions"},"category":"Natural Language Processing","categories":["Miscellaneous","Natural Language Processing","Reasoning"],"category_note":null,"description":"Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include [SQuAD](/dataset/squad), [HotPotQA](/dataset/hotpotqa), [bAbI](/dataset/babi-1), [TriviaQA](/dataset/triviaqa), [WikiQA](/dataset/wikiqa), and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.\r\n\r\n( Image credit: [SQuAD](https://rajpurkar.github.io/mlx/qa-and-squad/) )","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["P@1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"P@1":null}},"counts":{"rows":21,"rows_with_code":9,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"TimeR4","metrics":{"P@1":"78.1"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Quasar","metrics":{"P@1":"75.4"},"uses_additional_data":false,"paper_date":"2024-12-10","paper":"/paper/rag-based-question-answering-over","paper_url":"https://arxiv.org/abs/2412.07420v1","paper_title":"RAG-based Question Answering over Heterogeneous Data and Text","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"TwiRGCN","metrics":{"P@1":"60.5"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/twirgcn-temporally-weighted-graph-convolution","paper_url":"https://arxiv.org/abs/2210.06281v2","paper_title":"TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"EXAQT","metrics":{"P@1":"56.5"},"uses_additional_data":false,"paper_date":"2021-09-18","paper":"/paper/complex-temporal-question-answering-on","paper_url":"https://arxiv.org/abs/2109.08935v1","paper_title":"Complex Temporal Question Answering on Knowledge Graphs","code":"https://github.com/zhenjia2017/exaqt","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"SF-TQA","metrics":{"P@1":"53.9"},"uses_additional_data":false,"paper_date":"2022-10-10","paper":"/paper/semantic-framework-based-query-generation-for","paper_url":"https://arxiv.org/abs/2210.04490v3","paper_title":"Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"M3TQA","metrics":{"P@1":"53.6"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"FAITH","metrics":{"P@1":"53.5"},"uses_additional_data":false,"paper_date":"2024-02-23","paper":"/paper/faithful-temporal-question-answering-over","paper_url":"https://arxiv.org/abs/2402.15400v1","paper_title":"Faithful Temporal Question Answering over Heterogeneous Sources","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"LGQA","metrics":{"P@1":"52.9"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"EXPLAIGNN","metrics":{"P@1":"52.5"},"uses_additional_data":false,"paper_date":"2023-05-02","paper":"/paper/explainable-conversational-question-answering","paper_url":"https://arxiv.org/abs/2305.01548v2","paper_title":"Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks","code":"https://github.com/philippchr/explaignn","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"CTRN","metrics":{"P@1":"46.5"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"GRAFT-Net","metrics":{"P@1":"45.2"},"uses_additional_data":false,"paper_date":"2022-10-21","paper":"/paper/graphnet-graph-neural-networks-for-neutrino","paper_url":"https://arxiv.org/abs/2210.12194v1","paper_title":"GraphNeT: Graph neural networks for neutrino telescope event reconstruction","code":"https://github.com/graphnet-team/graphnet","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"TempoQR","metrics":{"P@1":"43.8"},"uses_additional_data":false,"paper_date":"2021-12-10","paper":"/paper/tempoqr-temporal-question-reasoning-over","paper_url":"https://arxiv.org/abs/2112.05785v1","paper_title":"TempoQR: Temporal Question Reasoning over Knowledge Graphs","code":"https://github.com/cmavro/tempoqr","n_code_links":3,"syntology":null},{"rank_in_archive_order":13,"model":"TMA","metrics":{"P@1":"43.6"},"uses_additional_data":false,"paper_date":"2023-02-24","paper":"/paper/time-aware-multiway-adaptive-fusion-network","paper_url":"https://arxiv.org/abs/2302.12529v2","paper_title":"Time-aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"UniK-QA","metrics":{"P@1":"42.4"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"Convinse","metrics":{"P@1":"42.3"},"uses_additional_data":false,"paper_date":"2022-04-25","paper":"/paper/conversational-question-answering-on","paper_url":"https://arxiv.org/abs/2204.11677v2","paper_title":"Conversational Question Answering on Heterogeneous Sources","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"CRONKGQA","metrics":{"P@1":"39.5"},"uses_additional_data":false,"paper_date":"2021-06-03","paper":"/paper/question-answering-over-temporal-knowledge","paper_url":"https://arxiv.org/abs/2106.01515v1","paper_title":"Question Answering Over Temporal Knowledge Graphs","code":"https://github.com/apoorvumang/CronKGQA","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"UniQorn","metrics":{"P@1":"33.1"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/uniqorn-unified-question-answering-over-rdf","paper_url":"https://arxiv.org/abs/2108.08614v9","paper_title":"UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text","code":"https://github.com/ajesujoba/UNIQORN","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"GPT-4","metrics":{"P@1":"30.6"},"uses_additional_data":false,"paper_date":"2023-09-22","paper":"/paper/openai-s-gpt4-as-coding-assistant","paper_url":"https://arxiv.org/abs/2309.12732v1","paper_title":"OpenAi's GPT4 as coding assistant","code":"https://github.com/lmous/openai-gpt4-coding-assistant","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"InstructGPT","metrics":{"P@1":"22.4"},"uses_additional_data":false,"paper_date":"2022-03-04","paper":"/paper/training-language-models-to-follow","paper_url":"https://arxiv.org/abs/2203.02155v1","paper_title":"Training language models to follow instructions with human feedback","code":"https://github.com/ggml-org/llama.cpp","n_code_links":11,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"Llama3","metrics":{"P@1":"17.8"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":26,"n_unverified":32,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":21,"model":"PullNet","metrics":{"P@1":"10.5"},"uses_additional_data":false,"paper_date":"2019-04-21","paper":"/paper/pullnet-open-domain-question-answering-with","paper_url":"http://arxiv.org/abs/1904.09537v1","paper_title":"PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":26,"n_unverified":42,"n_samples":68,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":26,"n_unverified":42,"n_samples":68,"n_pointer_only_licence":5,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}