{"url":"/dataset/gta","name":"GTA","full_name":"A Benchmark for General Tool Agents","description_markdown":"A benchmark to evaluate the tool-use capabilities of LLM-based agents in real-world scenarios.","description_withheld":null,"homepage":"https://open-compass.github.io/GTA/","introduced_date":"2024-07-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/gta-a-benchmark-for-general-tool-agents","title":"GTA: A Benchmark for General Tool Agents","first_author":"Jize Wang","url":null},"license":{"name":"Apache-2.0","url":"https://github.com/open-compass/GTA/blob/main/LICENSE.txt"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GTA"],"data_loaders":[],"num_papers_in_archive":8,"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."}