We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously ...
Thank you for your support and interest in this project. All scripts support additional options to enable optional libraries and disable platform architectures. See Building wiki page for the details.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results