{"url":"/sota/zero-shot-video-question-answer-on-egoschema","task":{"name":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","note":null},"dataset":{"name":"EgoSchema (subset)","url":"/dataset/egoschema"},"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","Inference Speed (s)"],"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","Inference Speed (s)":null}},"counts":{"rows":14,"rows_with_code":13,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Tarsier (34B)","metrics":{"Accuracy":"68.6"},"uses_additional_data":false,"paper_date":"2024-06-30","paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","paper_url":"https://arxiv.org/abs/2407.00634v2","paper_title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","code":"https://github.com/bytedance/tarsier","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"VideoChat-T (7B)","metrics":{"Accuracy":"68.4"},"uses_additional_data":false,"paper_date":"2024-10-25","paper":"/paper/timesuite-improving-mllms-for-long-video","paper_url":"https://arxiv.org/abs/2410.19702v2","paper_title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","code":"https://github.com/OpenGVLab/TimeSuite","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"LangRepo (12B)","metrics":{"Accuracy":"66.2"},"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":4,"model":"VideoTree (GPT4)","metrics":{"Accuracy":"66.2"},"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":5,"model":"LVNet","metrics":{"Accuracy":"66.0"},"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":6,"model":"VideoChat2_HD_mistral","metrics":{"Accuracy":"65.6"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/mvbench-a-comprehensive-multi-modal-video","paper_url":"https://arxiv.org/abs/2311.17005v4","paper_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","code":"https://github.com/opengvlab/ask-anything","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"VideoChat2_mistral","metrics":{"Accuracy":"63.6"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/mvbench-a-comprehensive-multi-modal-video","paper_url":"https://arxiv.org/abs/2311.17005v4","paper_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","code":"https://github.com/opengvlab/ask-anything","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"MVU (13B)","metrics":{"Accuracy":"60.3","Inference Speed (s)":"2.42"},"uses_additional_data":false,"paper_date":"2024-03-25","paper":"/paper/understanding-long-videos-in-one-multimodal","paper_url":"https://arxiv.org/abs/2403.16998v2","paper_title":"Understanding Long Videos with Multimodal Language Models","code":"https://github.com/kahnchana/mvu","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"TS-LLaVA-34B","metrics":{"Accuracy":"57.8"},"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":10,"model":"LLoVi (GPT-3.5)","metrics":{"Accuracy":"57.6"},"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":11,"model":"LLoVi (7B)","metrics":{"Accuracy":"50.8"},"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":"SlowFast-LLaVA-34B","metrics":{"Accuracy":"47.2"},"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":13,"model":"SeViLA (4B)","metrics":{"Accuracy":"25.7"},"uses_additional_data":false,"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":14,"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 6,264 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":13,"rows_with_any_sample_ran":13,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":11,"samples_over_distinct_papers":{"n_ran":60,"n_unverified":15,"n_samples":75,"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":73,"n_unverified":18,"n_samples":91,"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"}}}