{"paper":{"title":"MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alicia Lozano-Diez, Allison Ferner, Cecilia Bola\\~nos, Chao Zhang, David Harwath, Dinesh Manocha, Eleni Zanou, Fernando L\\'opez, Hyeonggon Ryu, Joon Son Chung, Lasha Koroshinadze, Laura Herrera-Alarc\\'on, Leibny Paola Garcia Perera, Lichang Chen, Maxim Pli\\v{c}ka, Miroslav Hlav\\'a\\v{c}ek, Nishit Anand, Ramani Duraiswami, Santosh Kesiraju, Sara Barahona, Sathvik Udupa, Satish Rahi, Satvik Dixit, Siddhi Patil, Siyuan Hou, Soham Deshmukh, Sonal Kumar, Sreyan Ghosh, Themos Stafylakis, Vaibhavi Lokegaonkar, \\v{S}imon Sedl\\'a\\v{c}ek, Wenyi Yu, William Fineas Ellingwood, Yao Liu","submitted_at":"2025-08-19T16:33:49Z","abstract_excerpt":"Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio understanding to qualify as generally intelligent. However, evaluating auditory intelligence comprehensively remains challenging. To address this gap, we introduce MMAU-Pro, the most comprehensive and rigorously curated benchmark for assessing audio intelligence in AI systems. MMAU-Pro contains 5,305 instances, where each instance has one or more audios paired with human expert-generated question-answer pairs, spanning s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13992","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.13992/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}