| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Qwen2-Audio Technical Report | ✓ Link | 93.92 | Qwen2-Audio | 2024-07-15 |
| VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs | ✓ Link | 93.19 | VideoLLaMA 2-AV 7B | 2024-06-11 |
| LongCat-Flash-Omni Technical Report | ✓ Link | 92.76 | LongCat-Flash-Omni | 2025-10-31 |
| ERNIE 5.0 Technical Report | 90.73 | ERNIE 5.0 | 2026-02-04 | |
| LongCat-Next: Lexicalizing Modalities as Discrete Tokens | ✓ Link | 85.91 | LongCat-Next (A3B, 68.5B) | 2026-03-29 |