{"url":"/sota/question-answering-on-multirc","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"MultiRC","url":"/dataset/multirc"},"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":["F1","EM"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher","EM":null}},"counts":{"rows":30,"rows_with_code":28,"rows_with_paper_page":30,"rows_dated":30,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PaLM 540B (finetuned)","metrics":{"EM":"69.2","F1":"90.1"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"syntology":{"n_ran":30,"n_unverified":7,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ST-MoE-32B 269B (fine-tuned)","metrics":{"F1":"89.6"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/designing-effective-sparse-expert-models","paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","code":"https://github.com/tensorflow/mesh","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":3,"model":"Turing NLR v5 XXL 5.4B (fine-tuned)","metrics":{"EM":"63","F1":"88.4"},"uses_additional_data":false,"paper_date":"2022-12-04","paper":"/paper/toward-efficient-language-model-pretraining","paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"DeBERTa-1.5B","metrics":{"EM":"63.7","F1":"88.2"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/deberta-decoding-enhanced-bert-with","paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3}},{"rank_in_archive_order":5,"model":"Vega v2 6B (fine-tuned)","metrics":{"EM":"62.4","F1":"88.2"},"uses_additional_data":false,"paper_date":"2022-12-04","paper":"/paper/toward-efficient-language-model-pretraining","paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"PaLM 2-L (one-shot)","metrics":{"F1":"88.2"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"T5-XXL 11B (fine-tuned)","metrics":{"F1":"88.1"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":2,"n_unverified":29,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"F1":"86"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/designing-effective-sparse-expert-models","paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","code":"https://github.com/tensorflow/mesh","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":9,"model":"PaLM 2-M (one-shot)","metrics":{"F1":"84.1"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"PaLM 2-S (one-shot)","metrics":{"F1":"84.0"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"FLAN 137B (prompt-tuned)","metrics":{"F1":"83.4"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"FLAN 137B (zero-shot)","metrics":{"F1":"77.5"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"GPT-3 175B (Few-Shot)","metrics":{"F1":"75.4"},"uses_additional_data":false,"paper_date":"2020-05-28","paper":"/paper/language-models-are-few-shot-learners","paper_url":"https://arxiv.org/abs/2005.14165v4","paper_title":"Language Models are Few-Shot Learners","code":"https://github.com/ggml-org/llama.cpp","n_code_links":67,"syntology":{"n_ran":15,"n_unverified":50,"n_samples":65,"n_pointer_only_licence":4}},{"rank_in_archive_order":14,"model":"FLAN 137B (1-shot)","metrics":{"F1":"72.1"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"KELM (finetuning BERT-large based single model)","metrics":{"EM":"27.2","F1":"70.8"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/kelm-knowledge-enhanced-pre-trained-language","paper_url":"https://arxiv.org/abs/2109.04223v2","paper_title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","code":"https://github.com/nlp-anonymous-happy/anonymous-kg-guided-nlp","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"BERT-large(single model)","metrics":{"EM":"24.1","F1":"70.0"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/bert-pre-training-of-deep-bidirectional","paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":534,"syntology":{"n_ran":204,"n_unverified":455,"n_samples":659,"n_pointer_only_licence":149}},{"rank_in_archive_order":17,"model":"Neo-6B (QA + WS)","metrics":{"F1":" 63.8"},"uses_additional_data":false,"paper_date":"2022-10-05","paper":"/paper/ask-me-anything-a-simple-strategy-for","paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","code":"https://github.com/hazyresearch/ama_prompting","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Bloomberg GPT 50B (1-shot)","metrics":{"F1":"62.3"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"N-Grammer 343M","metrics":{"EM":"11.3","F1":"62"},"uses_additional_data":false,"paper_date":"2022-07-13","paper":"/paper/n-grammer-augmenting-transformers-with-latent-1","paper_url":"https://arxiv.org/abs/2207.06366v1","paper_title":"N-Grammer: Augmenting Transformers with latent n-grams","code":"https://github.com/tensorflow/lingvo","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"Neo-6B (few-shot)","metrics":{"F1":"60.8"},"uses_additional_data":false,"paper_date":"2022-10-05","paper":"/paper/ask-me-anything-a-simple-strategy-for","paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","code":"https://github.com/hazyresearch/ama_prompting","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"AlexaTM 20B","metrics":{"F1":"59.6"},"uses_additional_data":false,"paper_date":"2022-08-02","paper":"/paper/alexatm-20b-few-shot-learning-using-a-large","paper_url":"https://arxiv.org/abs/2208.01448v2","paper_title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","code":"https://github.com/amazon-science/alexa-teacher-models","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"Neo-6B (QA)","metrics":{"F1":"58.8"},"uses_additional_data":false,"paper_date":"2022-10-05","paper":"/paper/ask-me-anything-a-simple-strategy-for","paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","code":"https://github.com/hazyresearch/ama_prompting","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"BLOOM 176B (1-shot)","metrics":{"F1":"26.7"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"GPT-NeoX 20B (1-shot)","metrics":{"F1":"22.9"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"OPT 66B (1-shot)","metrics":{"F1":"18.8"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null},{"rank_in_archive_order":26,"model":"T5-11B","metrics":{"EM":"63.3"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":2,"n_unverified":29,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"Hybrid H3 355M (3-shot, logit scoring)","metrics":{"EM":"59.7"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"Hybrid H3 355M (0-shot, logit scoring)","metrics":{"EM":"59.5"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"Hybrid H3 125M (0-shot, logit scoring)","metrics":{"EM":"51.4"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"Hybrid H3 125M (3-shot, logit scoring)","metrics":{"EM":"48.9"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/hungry-hungry-hippos-towards-language","paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","code":"https://github.com/hazyresearch/safari","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":0}}],"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":21,"rows_with_any_sample_ran":17,"distinct_papers_with_graph_line":12,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":271,"n_unverified":570,"n_samples":841,"n_pointer_only_licence":161,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":303,"n_unverified":625,"n_samples":928,"n_pointer_only_licence":166,"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"}}}