{"url":"/dataset/mm-vet-v2","name":"MM-Vet v2","full_name":null,"description_markdown":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","description_withheld":null,"homepage":"https://github.com/yuweihao/MM-Vet","introduced_date":"2024-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","first_author":"Weihao Yu","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MM-Vet v2"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet-v2","task":"Visual Question Answering","dataset_variant":"MM-Vet v2","rows":24,"metrics":["GPT-4 score","Params"],"first_row_in_archive_order":{"model":"gemini-2.0-flash-exp","paper":null,"metrics":{"GPT-4 score":"77.1±0.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/qwen2-vl-enhancing-vision-language-model-s","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","date":"2024-09-18","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":8,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/claude-3-5-sonnet-model-card-addendum","title":"Claude 3.5 Sonnet Model Card Addendum","date":"2024-06-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/how-far-are-we-to-gpt-4v-closing-the-gap-to","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","date":"2024-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internlm-xcomposer2-mastering-free-form-text","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","date":"2024-01-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generative-multimodal-models-are-in-context","title":"Generative Multimodal Models are In-Context Learners","date":"2023-12-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gemini-a-family-of-highly-capable-multimodal-1","title":"Gemini: A Family of Highly Capable Multimodal Models","date":"2023-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cogagent-a-visual-language-model-for-gui","title":"CogAgent: A Visual Language Model for GUI Agents","date":"2023-12-14","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":12,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cogvlm-visual-expert-for-pretrained-language","title":"CogVLM: Visual Expert for Pretrained Language Models","date":"2023-11-06","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/improved-baselines-with-visual-instruction","title":"Improved Baselines with Visual Instruction Tuning","date":"2023-10-05","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","date":"2023-08-24","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+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/openflamingo-an-open-source-framework-for","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","date":"2023-08-02","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mimic-it-multi-modal-in-context-instruction","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","date":"2023-06-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","rows_on_this_dataset":4,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":50,"samples_ran":31,"samples_unverified":19,"pointer_only_for_licence":11,"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."}