| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music | 75.76 | AF-Next-Captioner + GPT-5.2 | 2026-04-13 | |
| Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models | ✓ Link | 73.16 | Audio Flamingo 3 (+Think) | 2025-07-10 |
| AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives | ✓ Link | 72.5 | Qwen-Audio-AHA | 2025-12-30 |
| Covo-Audio Technical Report | 71.89 | Covo-Audio | 2026-02-10 | |
| DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding | 67.0 | DIFFA-2 (8B) | 2026-01-30 | |
| AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound | ✓ Link | 66.03 | AudSemThinker-QA GRPO | 2025-05-20 |
| Mellow: a small audio language model for reasoning | ✓ Link | 52.11 | Mellow | 2025-03-11 |
| MATS: An Audio Language Model under Text-only Supervision | ✓ Link | 44.5 | MATS-LLaMA | 2025-02-19 |