| Rank | Model | Score |
|---|---|---|
| 1 | lfm3-omni-2b | 51.4 |
1 phaseActive
A 1,000-item benchmark for deep reasoning across speech, audio, music, and mixed-modality audio, with four hierarchical reasoning layers (Signal, Perception, Semantic, Cultural).
Quick answer: MMAR ("A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix") is a benchmark introduced by Ziyang Ma, Yinghao Ma, Yanqiao Zhu, et al. (Shanghai Jiao Tong University and collaborators, submitted May 2025) with 1,000 curated audio-question-answer triplets drawn from real-world internet videos. Unlike benchmarks limited to one domain of sound, MMAR spans mixed-modality combinations of sound, music, and speech, and grades models across four hierarchical reasoning layers: Signal, Perception, Semantic, and Cultural.
Most audio benchmarks test a single domain (speech-only, music-only, or environmental-sound-only). MMAR instead curates real-world audio that mixes these domains together and requires multi-step reasoning beyond surface-level recognition — each question ships with a Chain-of-Thought rationale, and a subset demands graduate-level domain knowledge, raising the difficulty bar versus simpler audio QA sets.
| Model | Score | Source | Date |
|---|---|---|---|
| LFM3-Omni-2B | 51.40% | Liquid AI model card | 2026-10-27 |