ReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrieval

Abstract:Existing audio retrieval benchmarks primarily assess semantic matching, lacking comprehensive evaluation of the logical reasoning capabilities required by complex queries. We introduce ReasonAudio, a benchmark for reasoning-intensive Text-Audio Retrieval that evaluates four abilities: negation, temporal order, sound co-occurrence, and sound duration. It comprises five synthetic subtasks with 1,000 queries over 10,000 composite audio clips and a natural subtask with 100 queries over 1,000 real-world clips. Evaluation of 11 state-of-the-art retrieval systems reveals substantial limitations: the best-performing model, OmniEmbed-7B, achieves an overall score of 20.7. In a controlled experiment designed to reduce the influence of sound-event matching, OmniEmbed-7B attains 53.8% average accuracy, compared with 70.6% for its generative backbone, Qwen2.5-Omni-7B-Thinker, and 95.6% for humans. Our results highlight the challenges of reasoning-intensive audio retrieval and reveal a performance gap between OmniEmbed-7B and its generative backbone.

Artificial Intelligence (cs.AI)

arXiv:2605.03361 [cs.AI]

(or arXiv:2605.03361v3 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.03361 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.