| StepAudio 3 Realtime Technical Report | | 90.6 | StepAudio 3 Realtime | 2026-09-12 |
| ERNIE 5.0 Technical Report | | 84.68 | ERNIE 5.0 | 2026-02-04 |
| Qwen-Audio-Jev: A Unified Interface for Audio Decisions | | 84.0568 | Qwen-Audio-Jev | 2026-10-15 |
| FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation | ✓ Link | 83.3 | FireRedAudio | 2026-08-25 |
| Qwen3.5-Omni Technical Report | | 82.8 | Qwen3.5-Omni-Plus | 2026-04-21 |
| Step-Audio-R1.5 Technical Report | ✓ Link | 79.03 | Step-Audio-R1.5 | 2026-04-28 |
| Step-Audio-R1 Technical Report | ✓ Link | 75.9 | Step-Audio-R1 | 2025-11-19 |
| Qwen3-Omni Technical Report | ✓ Link | 71.3 | Qwen3-Omni-Flash-Thinking | 2025-09-22 |
| OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering | ✓ Link | 70.7 | OmniJigsaw (CMM) | 2026-04-09 |
| Fun-Audio-Chat Technical Report | ✓ Link | 70.1 | Fun-Audio-Chat-30B-A3B | 2025-12-23 |
| Realtime-Venus: A full-duplex interaction system with asynchronous delegation | | 66.8 | Realtime-Venus-Audio | 2026-09-12 |
| Covo-Audio Technical Report | | 66.64 | Covo-Audio | 2026-02-10 |
| Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs | | 66.2 | UAS-Audio | 2026-04-14 |
| Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning | ✓ Link | 65.9 | AudioRubrics Qwen2.5-Omni-7B (rubric weight 0.7) | 2026-08-03 |
| Unified Audio Intelligence Without Regressing on Text Intelligence | | 63.4 | Audex 30B-A3B | 2026-07-06 |
| MiMo-Audio: Audio Language Models are Few-Shot Learners | ✓ Link | 62.88 | MiMo-Audio-7B-Instruct (+Think) | 2025-09-01 |
| Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models | ✓ Link | 62.3 | Audio Flamingo 3 (+Think) | 2025-07-10 |
| Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos | | 61.5 | AVF-Instruct | 2026-07-17 |
| DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding | | 60.45 | DIFFA-2 (8B) | 2026-01-30 |
| Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing | ✓ Link | 56.83 | Audio-Omni | 2026-04-12 |
| DIFFA: Large Language Diffusion Models Can Listen and Understand | ✓ Link | 56.43 | DIFFA (rewrite-Qwen3 data) | 2025-07-24 |