{"url":"/sota/science-question-answering-on-scienceqa","task":{"name":"Science Question Answering","url":"/task/science-question-answering","note":null},"dataset":{"name":"ScienceQA","url":"/dataset/scienceqa"},"category":"Natural Language Processing","categories":["Miscellaneous","Natural Language Processing","Reasoning"],"category_note":null,"description":"Image credit: [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://paperswithcode.com/paper/learn-to-explain-multimodal-reasoning-via)","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":["Avg. Accuracy","Natural Science","Social Science","Language Science","Text Context","Image Context","No Context","Grades 1-6","Grades 7-12"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Avg. Accuracy":"higher","Natural Science":null,"Social Science":null,"Language Science":null,"Text Context":null,"Image Context":null,"No Context":null,"Grades 1-6":null,"Grades 7-12":null}},"counts":{"rows":10,"rows_with_code":9,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"MC-CoT F-Large","metrics":{"Avg. Accuracy":"94.88","Grades 1-6":"95.3","Grades 7-12":"94.13","Image Context":"93.75","Language Science":"93.18","Natural Science":"97.47","No Context":"94.49","Social Science":"90.44","Text Context":"96.97"},"uses_additional_data":false,"paper_date":"2023-11-23","paper":"/paper/boosting-the-power-of-small-multimodal","paper_url":"https://arxiv.org/abs/2311.14109v2","paper_title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","code":"https://github.com/chengtan9907/mc-cot","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"Honeybee","metrics":{"Avg. Accuracy":"94.39","Grades 1-6":"95.04","Grades 7-12":"93.21","Image Context":"93.75","Language Science":"91.18","Natural Science":"95.20","No Context":"93.17","Social Science":"96.29","Text Context":"94.48"},"uses_additional_data":true,"paper_date":"2023-12-11","paper":"/paper/honeybee-locality-enhanced-projector-for","paper_url":"https://arxiv.org/abs/2312.06742v2","paper_title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","code":"https://github.com/kakaobrain/honeybee","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":3,"model":"LLaVA (+ GPT-4)","metrics":{"Avg. Accuracy":"92.53"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"Multimodal CoT","metrics":{"Avg. Accuracy":"91.68","Grades 1-6":"92.44","Grades 7-12":"90.31","Image Context":"88.80","Language Science":"90.82","Natural Science":"95.91","No Context":"92.89","Social Science":"82.00","Text Context":"95.26"},"uses_additional_data":false,"paper_date":"2023-02-02","paper":"/paper/multimodal-chain-of-thought-reasoning-in","paper_url":"https://arxiv.org/abs/2302.00923v5","paper_title":"Multimodal Chain-of-Thought Reasoning in Language Models","code":"https://github.com/amazon-science/mm-cot","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":1}},{"rank_in_archive_order":5,"model":"Chat-UniVi-13B","metrics":{"Avg. Accuracy":"90.99","Grades 1-6":"91.19","Grades 7-12":"90.64","Image Context":"88.05","Language Science":"88.91","Natural Science":"90.41","No Context":"90.94","Social Science":"95.05","Text Context":"89.64"},"uses_additional_data":true,"paper_date":"2023-11-14","paper":"/paper/chat-univi-unified-visual-representation","paper_url":"https://arxiv.org/abs/2311.08046v3","paper_title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","code":"https://github.com/pku-yuangroup/chat-univi","n_code_links":4,"syntology":null},{"rank_in_archive_order":6,"model":"GPT-3 - CoT (QCM→ALE , 2-shot)","metrics":{"Avg. Accuracy":"75.17","Grades 1-6":"78.23","Grades 7-12":" 69.68","Image Context":"67.43","Language Science":"78.09","Natural Science":"75.44","No Context":"79.93","Social Science":"70.87","Text Context":"74.68"},"uses_additional_data":false,"paper_date":"2022-09-20","paper":"/paper/learn-to-explain-multimodal-reasoning-via","paper_url":"https://arxiv.org/abs/2209.09513v2","paper_title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","code":"https://github.com/lupantech/ScienceQA","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"GPT-3 - CoT(QCM→AE, 2-shot)","metrics":{"Avg. Accuracy":"74.61","Grades 1-6":"78.49","Grades 7-12":"67.63","Image Context":"66.09","Language Science":"77.55","Natural Science":"76.60","No Context":"79.58","Social Science":"65.92","Text Context":"75.51"},"uses_additional_data":false,"paper_date":"2022-09-20","paper":"/paper/learn-to-explain-multimodal-reasoning-via","paper_url":"https://arxiv.org/abs/2209.09513v2","paper_title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","code":"https://github.com/lupantech/ScienceQA","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":8,"model":"UnifiedQA-BASE - CoT (QCM→ALE)","metrics":{"Avg. Accuracy":"74.11","Grades 1-6":"77.06","Grades 7-12":"68.82","Image Context":"66.53","Language Science":"78.91","Natural Science":"71.00","No Context":"81.81","Social Science":"76.04","Text Context":"66.42"},"uses_additional_data":false,"paper_date":"2022-09-20","paper":"/paper/learn-to-explain-multimodal-reasoning-via","paper_url":"https://arxiv.org/abs/2209.09513v2","paper_title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","code":"https://github.com/lupantech/ScienceQA","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":9,"model":"GPT-3 (QCM→A, 2-shot)","metrics":{"Avg. Accuracy":"73.97","Grades 1-6":"76.80","Grades 7-12":" 68.89","Image Context":" 67.28","Language Science":"76.00","Natural Science":"74.64","No Context":"77.42","Social Science":"69.74","Text Context":"74.44"},"uses_additional_data":false,"paper_date":"2022-09-20","paper":"/paper/learn-to-explain-multimodal-reasoning-via","paper_url":"https://arxiv.org/abs/2209.09513v2","paper_title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","code":"https://github.com/lupantech/ScienceQA","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":10,"model":"Video-LaVIT","metrics":{"Avg. Accuracy":"70.0"},"uses_additional_data":false,"paper_date":"2024-02-05","paper":"/paper/video-lavit-unified-video-language-pre","paper_url":"https://arxiv.org/abs/2402.03161v3","paper_title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","code":"https://github.com/jy0205/lavit","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5}}],"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":8,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":17,"n_unverified":8,"n_samples":25,"n_pointer_only_licence":12,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":29,"n_unverified":11,"n_samples":40,"n_pointer_only_licence":18,"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"}}}