| Paper | Code | MMAU-Pro Overall Weighted Performance | ModelName | ReleaseDate |
|---|---|---|---|---|
| dots3-note Preview: A Small but Mighty Step Toward Long-Horizon Agency in Real Life | ✓ Link | 69.79 | dots3-note Preview | 2026-08-13 |
| Realtime-Venus: A full-duplex interaction system with asynchronous delegation | 63.2 | Realtime-Venus-Audio | 2026-09-12 | |
| Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music | 58.7 | AF-Next-Think | 2026-04-13 | |
| AudioToolAgent: An Agentic Framework for Audio-Language Models | ✓ Link | 57.96 | AudioToolAgent | 2025-10-03 |
| AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives | ✓ Link | 54.8 | Qwen-Audio-AHA | 2025-12-30 |
| MiMo-Audio: Audio Language Models are Few-Shot Learners | ✓ Link | 53.35 | MiMo-Audio-7B-Instruct | 2025-09-01 |