{"url":"/sota/zeroshot-video-question-answer-on-activitynet","task":{"name":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","note":null},"dataset":{"name":"ActivityNet-QA","url":"/dataset/activitynet-qa"},"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","Confidence Score"],"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","Confidence Score":"higher"}},"counts":{"rows":28,"rows_with_code":28,"rows_with_paper_page":28,"rows_dated":28,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Tarsier (34B)","metrics":{"Accuracy":"61.6","Confidence Score":"3.7"},"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":"PLLaVA (34B)","metrics":{"Accuracy":"60.9","Confidence Score":"3.7"},"uses_additional_data":false,"paper_date":"2024-04-25","paper":"/paper/pllava-parameter-free-llava-extension-from-1","paper_url":"https://arxiv.org/abs/2404.16994v2","paper_title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","code":"https://github.com/magic-research/PLLaVA","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"PPLLaVA-7B","metrics":{"Accuracy":"60.7","Confidence Score":"3.6"},"uses_additional_data":false,"paper_date":"2024-11-04","paper":"/paper/ppllava-varied-video-sequence-understanding","paper_url":"https://arxiv.org/abs/2411.02327v2","paper_title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","code":"https://github.com/farewellthree/ppllava","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":3}},{"rank_in_archive_order":4,"model":"LinVT-Qwen2-VL(7B)","metrics":{"Accuracy":"60.1","Confidence Score":"3.6"},"uses_additional_data":false,"paper_date":"2024-12-06","paper":"/paper/linvt-empower-your-image-level-large-language","paper_url":"https://arxiv.org/abs/2412.05185v2","paper_title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","code":"https://github.com/gls0425/linvt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":8,"n_samples":12,"n_pointer_only_licence":12}},{"rank_in_archive_order":5,"model":"SlowFast-LLaVA-34B","metrics":{"Accuracy":"59.2","Confidence Score":"3.5"},"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":6,"model":"TS-LLaVA-34B","metrics":{"Accuracy":"58.9","Confidence Score":"3.5"},"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":7,"model":"IG-VLM","metrics":{"Accuracy":"58.4","Confidence Score":"3.5"},"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":8,"model":"LLaVA-Mini","metrics":{"Accuracy":"53.5","Confidence Score":"3.5"},"uses_additional_data":false,"paper_date":"2025-01-07","paper":"/paper/llava-mini-efficient-image-and-video-large","paper_url":"https://arxiv.org/abs/2501.03895v1","paper_title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","code":"https://github.com/ictnlp/llava-mini","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"Flash-VStream","metrics":{"Accuracy":"51.9","Confidence Score":"3.4"},"uses_additional_data":false,"paper_date":"2024-06-12","paper":"/paper/flash-vstream-memory-based-real-time","paper_url":"https://arxiv.org/abs/2406.08085v2","paper_title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","code":"https://github.com/IVGSZ/Flash-VStream","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"ST-LLM","metrics":{"Accuracy":"50.9","Confidence Score":"3.3"},"uses_additional_data":false,"paper_date":"2024-03-30","paper":"/paper/st-llm-large-language-models-are-effective-1","paper_url":"https://arxiv.org/abs/2404.00308v1","paper_title":"ST-LLM: Large Language Models Are Effective Temporal Learners","code":"https://github.com/TencentARC/ST-LLM","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"VideoGPT+","metrics":{"Accuracy":"50.6","Confidence Score":"3.6"},"uses_additional_data":false,"paper_date":"2024-06-13","paper":"/paper/videogpt-integrating-image-and-video-encoders","paper_url":"https://arxiv.org/abs/2406.09418v1","paper_title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","code":"https://github.com/mbzuai-oryx/videogpt-plus","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":12,"model":"CAT-7B","metrics":{"Accuracy":"50.2","Confidence Score":"3.5"},"uses_additional_data":false,"paper_date":"2024-03-07","paper":"/paper/cat-enhancing-multimodal-large-language-model","paper_url":"https://arxiv.org/abs/2403.04640v1","paper_title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","code":"https://github.com/rikeilong/bay-cat","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":6,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"Video-LaVIT","metrics":{"Accuracy":"50.1","Confidence Score":"3.3"},"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}},{"rank_in_archive_order":14,"model":"VideoChat2","metrics":{"Accuracy":"49.1","Confidence Score":"3.3"},"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":15,"model":"LLaMA-VID-13B (2 Token)","metrics":{"Accuracy":"47.5","Confidence Score":"3.3"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/llama-vid-an-image-is-worth-2-tokens-in-large","paper_url":"https://arxiv.org/abs/2311.17043v1","paper_title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","code":"https://github.com/lastmile-ai/aiconfig","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"LLaMA-VID-7B (2 Token)","metrics":{"Accuracy":"47.4","Confidence Score":"3.3"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/llama-vid-an-image-is-worth-2-tokens-in-large","paper_url":"https://arxiv.org/abs/2311.17043v1","paper_title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","code":"https://github.com/lastmile-ai/aiconfig","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"Chat-UniVi-13B","metrics":{"Accuracy":"46.4","Confidence Score":"3.6"},"uses_additional_data":false,"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":18,"model":"MiniGPT4-video-7B","metrics":{"Accuracy":"46.3"},"uses_additional_data":false,"paper_date":"2024-04-04","paper":"/paper/minigpt4-video-advancing-multimodal-llms-for","paper_url":"https://arxiv.org/abs/2404.03413v1","paper_title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","code":"https://github.com/Vision-CAIR/MiniGPT4-video","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"Chat-UniVi","metrics":{"Accuracy":"46.1","Confidence Score":"3.3"},"uses_additional_data":false,"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":20,"model":"BT-Adapter (zero-shot)","metrics":{"Accuracy":"46.1","Confidence Score":"3.2"},"uses_additional_data":false,"paper_date":"2023-09-27","paper":"/paper/one-for-all-video-conversation-is-feasible","paper_url":"https://arxiv.org/abs/2309.15785v2","paper_title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","code":"https://github.com/farewellthree/BT-Adapter","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"MovieChat","metrics":{"Accuracy":"45.7","Confidence Score":"3.1"},"uses_additional_data":false,"paper_date":"2023-07-31","paper":"/paper/moviechat-from-dense-token-to-sparse-memory","paper_url":"https://arxiv.org/abs/2307.16449v4","paper_title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","code":"https://github.com/rese1f/MovieChat","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"Video-LLaVA","metrics":{"Accuracy":"45.3","Confidence Score":"3.3"},"uses_additional_data":false,"paper_date":"2023-11-16","paper":"/paper/video-llava-learning-united-visual-1","paper_url":"https://arxiv.org/abs/2311.10122v3","paper_title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","code":"https://github.com/PKU-YuanGroup/Video-LLaVA","n_code_links":6,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":23,"model":"Elysium","metrics":{"Accuracy":"43.4","Confidence Score":"2.9"},"uses_additional_data":false,"paper_date":"2024-03-25","paper":"/paper/elysium-exploring-object-level-perception-in","paper_url":"https://arxiv.org/abs/2403.16558v2","paper_title":"Elysium: Exploring Object-level Perception in Videos via MLLM","code":"https://github.com/hon-wong/elysium","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":24,"model":"Video-ChatGPT","metrics":{"Accuracy":"35.2","Confidence Score":"2.7"},"uses_additional_data":false,"paper_date":"2023-06-08","paper":"/paper/video-chatgpt-towards-detailed-video","paper_url":"https://arxiv.org/abs/2306.05424v2","paper_title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","code":"https://github.com/mbzuai-oryx/video-chatgpt","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"LLaMA Adapter","metrics":{"Accuracy":"34.2","Confidence Score":"2.7"},"uses_additional_data":false,"paper_date":"2023-04-28","paper":"/paper/llama-adapter-v2-parameter-efficient-visual","paper_url":"https://arxiv.org/abs/2304.15010v1","paper_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","code":"https://github.com/opengvlab/llama-adapter","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":26,"model":"Video Chat","metrics":{"Accuracy":"26.5","Confidence Score":"2.2"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/videochat-chat-centric-video-understanding","paper_url":"https://arxiv.org/abs/2305.06355v2","paper_title":"VideoChat: Chat-Centric Video Understanding","code":"https://github.com/opengvlab/ask-anything","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"FrozenBiLM","metrics":{"Accuracy":"24.7","Confidence Score":"-"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/zero-shot-video-question-answering-via-frozen","paper_url":"https://arxiv.org/abs/2206.08155v2","paper_title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","code":"https://github.com/antoyang/FrozenBiLM","n_code_links":3,"syntology":{"n_ran":14,"n_unverified":20,"n_samples":34,"n_pointer_only_licence":1}},{"rank_in_archive_order":28,"model":"Video LLaMA","metrics":{"Accuracy":"12.4","Confidence Score":"1.1"},"uses_additional_data":false,"paper_date":"2023-06-05","paper":"/paper/video-llama-an-instruction-tuned-audio-visual","paper_url":"https://arxiv.org/abs/2306.02858v4","paper_title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","code":"https://github.com/damo-nlp-sg/video-llama","n_code_links":4,"syntology":{"n_ran":18,"n_unverified":7,"n_samples":25,"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 6,264 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":22,"rows_with_any_sample_ran":20,"distinct_papers_with_graph_line":21,"distinct_papers_with_any_sample_ran":19,"samples_over_distinct_papers":{"n_ran":101,"n_unverified":78,"n_samples":179,"n_pointer_only_licence":60,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":104,"n_unverified":79,"n_samples":183,"n_pointer_only_licence":60,"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"}}}