{"url":"/dataset/spider2-v","name":"Spider2-V","full_name":"Spider2-V","description_markdown":"A multimodal agent benchmark on professional data science and engineering.\r\n* 494 real-world tasks, ranging from data warehousing to orchestration;\r\n* 20 professional enterprise-level applications (e.g., BigQuery, dbt, Airbyte, etc.);\r\n* both command line (CLI) and graphical user interfaces (GUI);\r\n* an interactive executable computer environment;\r\n* a document warehouse for agent retrieval.","description_withheld":null,"homepage":"https://spider2-v.github.io/","introduced_date":"2024-07-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/spider2-v-how-far-are-multimodal-agents-from","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","first_author":"Ruisheng Cao","url":null},"license":{"name":"Apache-2.0 license","url":"https://www.apache.org/licenses/LICENSE-2.0.txt"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Interactive","url":"/datasets/modality/interactive"},{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"},{"name":"AI Agent","url":"/task/ai-agent","datasets_with_task":"/datasets/task/ai-agent"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Spider2-V"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}