{"url":"/sota/zero-shot-video-question-answer-on-intentqa","task":{"name":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","note":null},"dataset":{"name":"IntentQA","url":"/dataset/intentqa"},"category":"Computer Vision","categories":["Computer Vision","Miscellaneous","Natural Language Processing","Reasoning"],"category_note":null,"description":"This task present the results of Zeroshot Question Answer results on TGIF-QA dataset for LLM powered Video Conversational Models.","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":13,"rows_with_code":11,"rows_with_paper_page":12,"rows_dated":12,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"ENTER","metrics":{"Accuracy":"71.5"},"uses_additional_data":false,"paper_date":"2025-01-24","paper":"/paper/enter-event-based-interpretable-reasoning-for","paper_url":"https://arxiv.org/abs/2501.14194v1","paper_title":"ENTER: Event Based Interpretable Reasoning for VideoQA","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"LVNet","metrics":{"Accuracy":"71.1"},"uses_additional_data":false,"paper_date":"2024-06-13","paper":"/paper/too-many-frames-not-all-useful-efficient","paper_url":"https://arxiv.org/abs/2406.09396v4","paper_title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","code":"https://github.com/jongwoopark7978/LVNet","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":"TS-LLaVA-34B","metrics":{"Accuracy":"67.9"},"uses_additional_data":false,"paper_date":"2024-11-17","paper":"/paper/ts-llava-constructing-visual-tokens-through","paper_url":"https://arxiv.org/abs/2411.11066v1","paper_title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","code":"https://github.com/tingyu215/ts-llava","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"VidCtx (7B)","metrics":{"Accuracy":"67.1"},"uses_additional_data":false,"paper_date":"2024-12-23","paper":"/paper/vidctx-context-aware-video-question-answering","paper_url":"https://arxiv.org/abs/2412.17415v2","paper_title":"VidCtx: Context-aware Video Question Answering with Image Models","code":"https://github.com/idt-iti/vidctx","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"VideoTree (GPT4)","metrics":{"Accuracy":"66.9"},"uses_additional_data":false,"paper_date":"2024-05-29","paper":"/paper/videotree-adaptive-tree-based-video","paper_url":"https://arxiv.org/abs/2405.19209v2","paper_title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","code":"https://github.com/Ziyang412/VideoTree","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":0,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"IG-VLM","metrics":{"Accuracy":"65.3"},"uses_additional_data":false,"paper_date":"2024-03-27","paper":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","paper_url":"https://arxiv.org/abs/2403.18406v1","paper_title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","code":"https://github.com/imagegridworth/IG-VLM","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"LLoVi (GPT-4)","metrics":{"Accuracy":"64.0"},"uses_additional_data":false,"paper_date":"2023-12-28","paper":"/paper/a-simple-llm-framework-for-long-range-video","paper_url":"https://arxiv.org/abs/2312.17235v3","paper_title":"A Simple LLM Framework for Long-Range Video Question-Answering","code":"https://github.com/ceezh/llovi","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SeViLA (4B)","metrics":{"Accuracy":"60.9"},"uses_additional_data":true,"paper_date":"2023-05-11","paper":"/paper/self-chained-image-language-model-for-video-1","paper_url":"https://arxiv.org/abs/2305.06988v2","paper_title":"Self-Chained Image-Language Model for Video Localization and Question Answering","code":"https://github.com/yui010206/sevila","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":9,"model":"SlowFast-LLaVA-34B","metrics":{"Accuracy":"60.1"},"uses_additional_data":false,"paper_date":"2024-07-22","paper":"/paper/slowfast-llava-a-strong-training-free","paper_url":"https://arxiv.org/abs/2407.15841v2","paper_title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","code":"https://github.com/apple/ml-slowfast-llava","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":10,"model":"LangRepo (12B)","metrics":{"Accuracy":"59.1"},"uses_additional_data":false,"paper_date":"2024-03-21","paper":"/paper/language-repository-for-long-video","paper_url":"https://arxiv.org/abs/2403.14622v2","paper_title":"Language Repository for Long Video Understanding","code":"https://github.com/kkahatapitiya/langrepo","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"LLoVi (7B)","metrics":{"Accuracy":"53.6"},"uses_additional_data":false,"paper_date":"2023-12-28","paper":"/paper/a-simple-llm-framework-for-long-range-video","paper_url":"https://arxiv.org/abs/2312.17235v3","paper_title":"A Simple LLM Framework for Long-Range Video Question-Answering","code":"https://github.com/ceezh/llovi","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"Mistral (7B)","metrics":{"Accuracy":"50.4"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/mistral-7b","paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","code":"https://github.com/mistralai/mistral-src","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"Random","metrics":{"Accuracy":"20.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":10,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":56,"n_unverified":11,"n_samples":67,"n_pointer_only_licence":17,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":62,"n_unverified":11,"n_samples":73,"n_pointer_only_licence":17,"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"}}}