{"url":"/dataset/mvbench","name":"MVBench","full_name":null,"description_markdown":"MVBench is a comprehensive Multi-modal Video understanding Benchmark. It was introduced to evaluate the comprehension capabilities of Multi-modal Large Language Models (MLLMs), particularly their temporal understanding in dynamic video tasks. MVBench covers 20 challenging video tasks that cannot be effectively solved with a single frame. It introduces a novel static-to-dynamic method to define these temporal-related tasks. By transforming various static tasks into dynamic ones, it enables the systematic generation of video tasks that require a broad spectrum of temporal skills, ranging from perception to cognition.","description_withheld":null,"homepage":"https://github.com/OpenGVLab/Ask-Anything/tree/main/video_chat2","introduced_date":"2023-11-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","first_author":"Kunchang Li","url":null},"license":null,"modalities":[],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","datasets_with_task":"/datasets/task/zeroshot-video-question-answer"}],"languages":[],"variants":["MVBench"],"data_loaders":[],"num_papers_in_archive":139,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-question-answering-on-mvbench","task":"Video Question Answering","dataset_variant":"MVBench","rows":22,"metrics":["Avg."],"first_row_in_archive_order":{"model":"LinVT-Qwen2-VL\n(7B)","paper":"/paper/linvt-empower-your-image-level-large-language","metrics":{"Avg.":"69.3"},"code_links":[{"title":"gls0425/linvt","url":"https://github.com/gls0425/linvt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-video-question-answer-on-mvbench","task":"Zero-Shot Video Question Answer","dataset_variant":"MVBench","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TS-LLaVA-34B","paper":"/paper/ts-llava-constructing-visual-tokens-through","metrics":{"Accuracy":"52.6"},"code_links":[{"title":"tingyu215/ts-llava","url":"https://github.com/tingyu215/ts-llava"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-vqa-on-mvbench","task":"Visual Question Answering (VQA)","dataset_variant":"MVBench","rows":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"Lyra-Pro","paper":"/paper/lyra-an-efficient-and-speech-centric","metrics":{"Acc":"72.3"},"code_links":[{"title":"dvlab-research/Lyra","url":"https://github.com/dvlab-research/Lyra"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/lyra-an-efficient-and-speech-centric","title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","date":"2024-12-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":19,"samples_ran":3,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":12,"samples_ran":4,"samples_unverified":8,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ts-llava-constructing-visual-tokens-through","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","date":"2024-11-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ppllava-varied-video-sequence-understanding","title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","date":"2024-11-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":2,"samples_unverified":7,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/timesuite-improving-mllms-for-long-video","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","date":"2024-10-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/longvu-spatiotemporal-adaptive-compression","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","date":"2024-10-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":6,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/oryx-mllm-on-demand-spatial-temporal","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","date":"2024-09-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mplug-owl3-towards-long-image-sequence","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","date":"2024-08-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","date":"2024-06-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/videogpt-integrating-image-and-video-encoders","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","date":"2024-06-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":17,"samples_ran":9,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pllava-parameter-free-llava-extension-from-1","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","date":"2024-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/st-llm-large-language-models-are-effective-1","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","date":"2024-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/hawkeye-training-video-text-llms-for","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","date":"2024-03-15","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sphinx-x-scaling-data-and-parameters-for-a","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","date":"2024-02-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/video-chatgpt-towards-detailed-video","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","date":"2023-06-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/video-llama-an-instruction-tuned-audio-visual","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","date":"2023-06-05","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":25,"samples_ran":18,"samples_unverified":7,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/instructblip-towards-general-purpose-vision","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","date":"2023-05-11","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/videochat-chat-centric-video-understanding","title":"VideoChat: Chat-Centric Video Understanding","date":"2023-05-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/minigpt-4-enhancing-vision-language","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","date":"2023-04-20","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":51,"samples_ran":16,"samples_unverified":35,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":18,"samples_harvested":220,"samples_ran":113,"samples_unverified":107,"pointer_only_for_licence":46,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}