{"url":"/sota/video-question-answering-on-mvbench","task":{"name":"Video Question Answering","url":"/task/video-question-answering","note":null},"dataset":{"name":"MVBench","url":"/dataset/mvbench"},"category":"Computer Vision","categories":["Computer Vision","Reasoning"],"category_note":null,"description":null,"description_from":null,"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."],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Avg.":null}},"counts":{"rows":22,"rows_with_code":22,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LinVT-Qwen2-VL\n(7B)","metrics":{"Avg.":"69.3"},"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":2,"model":"Tarsier (34B)","metrics":{"Avg.":"67.6"},"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":3,"model":"InternVideo2","metrics":{"Avg.":"67.2"},"uses_additional_data":false,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"LongVU (7B)","metrics":{"Avg.":"66.9"},"uses_additional_data":false,"paper_date":"2024-10-22","paper":"/paper/longvu-spatiotemporal-adaptive-compression","paper_url":"https://arxiv.org/abs/2410.17434v1","paper_title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","code":"https://github.com/Vision-CAIR/LongVU","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Oryx(34B)","metrics":{"Avg.":"64.7"},"uses_additional_data":false,"paper_date":"2024-09-19","paper":"/paper/oryx-mllm-on-demand-spatial-temporal","paper_url":"https://arxiv.org/abs/2409.12961v3","paper_title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","code":"https://github.com/oryx-mllm/oryx","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"VideoLLaMA2 (72B)","metrics":{"Avg.":"62.0"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/videollama-2-advancing-spatial-temporal","paper_url":"https://arxiv.org/abs/2406.07476v3","paper_title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","code":"https://github.com/damo-nlp-sg/videollama2","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"VideoChat-T (7B)","metrics":{"Avg.":"59.9"},"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":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"mPLUG-Owl3(7B)","metrics":{"Avg.":"59.5"},"uses_additional_data":false,"paper_date":"2024-08-09","paper":"/paper/mplug-owl3-towards-long-image-sequence","paper_url":"https://arxiv.org/abs/2408.04840v2","paper_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","code":"https://github.com/x-plug/mplug-owl","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"PPLLaVA (7b)","metrics":{"Avg.":"59.2"},"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":10,"model":"VideoGPT+","metrics":{"Avg.":"58.7"},"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":11,"model":"PLLaVA","metrics":{"Avg.":"58.1"},"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":12,"model":"ST-LLM","metrics":{"Avg.":"54.9"},"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":13,"model":"VideoChat2","metrics":{"Avg.":"51.9"},"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":14,"model":"HawkEye","metrics":{"Avg.":"47.55"},"uses_additional_data":false,"paper_date":"2024-03-15","paper":"/paper/hawkeye-training-video-text-llms-for","paper_url":"https://arxiv.org/abs/2403.10228v1","paper_title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","code":"https://github.com/yellow-binary-tree/hawkeye","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":15,"model":"SPHINX-Plus","metrics":{"Avg.":"39.7"},"uses_additional_data":false,"paper_date":"2024-02-08","paper":"/paper/sphinx-x-scaling-data-and-parameters-for-a","paper_url":"https://arxiv.org/abs/2402.05935v2","paper_title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","code":"https://github.com/alpha-vllm/llama2-accessory","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":16,"model":"TimeChat","metrics":{"Avg.":"38.5"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/timechat-a-time-sensitive-multimodal-large","paper_url":"https://arxiv.org/abs/2312.02051v2","paper_title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","code":"https://github.com/renshuhuai-andy/timechat","n_code_links":2,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"LLaVa","metrics":{"Avg.":"36.0"},"uses_additional_data":false,"paper_date":"2023-04-17","paper":"/paper/visual-instruction-tuning-1","paper_url":"https://arxiv.org/abs/2304.08485v2","paper_title":"Visual Instruction Tuning","code":"https://github.com/huggingface/transformers","n_code_links":13,"syntology":{"n_ran":16,"n_unverified":35,"n_samples":51,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"VideoChat","metrics":{"Avg.":"35.5"},"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":19,"model":"VideoLLaMA","metrics":{"Avg.":"34.1"},"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}},{"rank_in_archive_order":20,"model":"Video-ChatGPT","metrics":{"Avg.":"32.7"},"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":21,"model":"InstructBLIP","metrics":{"Avg.":"32.5"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/instructblip-towards-general-purpose-vision","paper_url":"https://arxiv.org/abs/2305.06500v2","paper_title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","code":"https://github.com/salesforce/lavis","n_code_links":4,"syntology":null},{"rank_in_archive_order":22,"model":"MiniGPT4","metrics":{"Avg.":"18.8"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/minigpt-4-enhancing-vision-language","paper_url":"https://arxiv.org/abs/2304.10592v2","paper_title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","code":"https://github.com/vision-cair/minigpt-4","n_code_links":6,"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 6,821 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":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"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":16,"rows_with_any_sample_ran":15,"distinct_papers_with_graph_line":16,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":105,"n_unverified":85,"n_samples":190,"n_pointer_only_licence":46,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":105,"n_unverified":85,"n_samples":190,"n_pointer_only_licence":46,"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"}}}