Audio Language Modeling on sStoryCloze
68.55AccuracyLLaMA-Omni2
Evaluation Results
| Method | Links | |
|---|---|---|
| LLaMA-Omni22026.01 | 68.55 | |
| MoST2026.01 | 65.43 | |
| Phi-4 Multimodal2026.01 | 62.39 | |
| MinMo2026.01 | 61.29 | |
| spiritLM2026.01 | 58.95 | |
| SpeechGPT2026.01 | 53.13 | |
| Moshi2026.01 | 45.16 |