{"url":"/sota/question-answering-on-storycloze","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"StoryCloze","url":"/dataset/storycloze"},"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":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":23,"rows_with_code":15,"rows_with_paper_page":23,"rows_dated":23,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"BLOOMZ","metrics":{"Accuracy":"96.3"},"uses_additional_data":false,"paper_date":"2022-11-03","paper":"/paper/crosslingual-generalization-through-multitask","paper_url":"https://arxiv.org/abs/2211.01786v2","paper_title":"Crosslingual Generalization through Multitask Finetuning","code":"https://github.com/bigscience-workshop/xmtf","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Flipped-3B","metrics":{"Accuracy":"95.88"},"uses_additional_data":false,"paper_date":"2022-10-06","paper":"/paper/guess-the-instruction-making-language-models","paper_url":"https://arxiv.org/abs/2210.02969v4","paper_title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","code":"https://github.com/seonghyeonye/flipped-learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"FLAN 137B (few-shot, k=10)","metrics":{"Accuracy":"94.7"},"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":4,"model":"T0-3B (CoT fine-tuned)","metrics":{"Accuracy":"94.5"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/the-cot-collection-improving-zero-shot-and","paper_url":"https://arxiv.org/abs/2305.14045v2","paper_title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","code":"https://github.com/kaistai/cot-collection","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"KiC-770M","metrics":{"Accuracy":"94.40"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/knowledge-in-context-towards-knowledgeable","paper_url":"https://arxiv.org/abs/2210.16433v3","paper_title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"FLAN 137B (zero-shot)","metrics":{"Accuracy":"93.4"},"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":7,"model":"Reading Strategies Model","metrics":{"Accuracy":"88.3"},"uses_additional_data":false,"paper_date":"2018-10-31","paper":"/paper/improving-machine-reading-comprehension-with","paper_url":"http://arxiv.org/abs/1810.13441v2","paper_title":"Improving Machine Reading Comprehension with General Reading Strategies","code":"https://github.com/nlpdata/strategy","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Finetuned Transformer LM","metrics":{"Accuracy":"86.5"},"uses_additional_data":false,"paper_date":"2018-06-11","paper":"/paper/improving-language-understanding-by","paper_url":"https://s3-us-west-2.amazonaws.com/openai-assets/research-covers/language-unsupervised/language_understanding_paper.pdf","paper_title":"Improving Language Understanding by Generative Pre-Training","code":"https://github.com/huggingface/transformers","n_code_links":13,"syntology":null},{"rank_in_archive_order":9,"model":"RoE-3B","metrics":{"Accuracy":"86.33"},"uses_additional_data":false,"paper_date":"2023-02-07","paper":"/paper/exploring-the-benefits-of-training-expert","paper_url":"https://arxiv.org/abs/2302.03202v2","paper_title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","code":"https://github.com/joeljang/rlphf","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":10,"model":"OPT-175B","metrics":{"Accuracy":"79.82"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":11,"model":"SparseGPT (175B, 50% Sparsity)","metrics":{"Accuracy":"78.87"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":12,"model":"Memory chains and semantic supervision","metrics":{"Accuracy":"78.7"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/unimelb-at-semeval-2016-tasks-4a-and-4b-an","paper_url":"https://aclanthology.org/S16-1027","paper_title":"UNIMELB at SemEval-2016 Tasks 4A and 4B: An Ensemble of Neural Networks and a Word2Vec Based Model for Sentiment Classification","code":"https://github.com/liufly/narrative-modeling","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Hidden Coherence Model","metrics":{"Accuracy":"77.6"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/story-comprehension-for-predicting-what","paper_url":"https://aclanthology.org/D17-1168","paper_title":"Story Comprehension for Predicting What Happens Next","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"SparseGPT (175B, 4:8 Sparsity)","metrics":{"Accuracy":"77.02"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":15,"model":"val-LS-skip","metrics":{"Accuracy":"76.5"},"uses_additional_data":false,"paper_date":"2018-03-15","paper":"/paper/a-simple-and-effective-approach-to-the-story","paper_url":"http://arxiv.org/abs/1803.05547v1","paper_title":"A Simple and Effective Approach to the Story Cloze Test","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"SparseGPT (175B, 2:4 Sparsity)","metrics":{"Accuracy":"76.19"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":17,"model":"sMLP – deterministic 9.4B (0-shot)","metrics":{"Accuracy":"74.7"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"Switch Transformer 9B","metrics":{"Accuracy":"73.3"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"GPT-3 Large 760M (zero-shot)","metrics":{"Accuracy":"72.4"},"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":41,"n_unverified":24,"n_samples":65,"n_pointer_only_licence":4}},{"rank_in_archive_order":20,"model":"Gshard 9B","metrics":{"Accuracy":"67.9"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"HASH Layers 10B (0-shot)","metrics":{"Accuracy":"64.7"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"Base Layers 10B (0-shot)","metrics":{"Accuracy":"61.4"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"OPT-175B (50% Sparsity)","metrics":{"Accuracy":"47.10"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9}}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":10,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":57,"n_unverified":28,"n_samples":85,"n_pointer_only_licence":16,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":93,"n_unverified":41,"n_samples":134,"n_pointer_only_licence":52,"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"}}}