| Model,openhermes_audio_test,alpaca_audio_test | |
| Qwen-Audio-Chat,10.6,9.8 | |
| hy_whisper_local_cs,, | |
| Qwen2-Audio-7B-Instruct,44.8,52.599999999999994 | |
| whisper_large_v3,, | |
| old_models,, | |
| gemini-1.5-flash,, | |
| WavLLM_fairseq,19.2,21.6 | |
| MERaLiON-AudioLLM-Whisper-SEA-LION,66.39999999999999,75.19999999999999 | |
| MERaLiON-AudioLLM-v2-2b,12.6,25.6 | |
| MERaLiON-AudioLLM-v2-9b,66.2,74.2 | |
| MERaLiON-AudioLLM-v2-9b-asr,10.0,16.8 | |
| Qwen2.5-Omni-3B,66.0,64.0 | |
| Qwen2.5-Omni-7B,57.400000000000006,59.2 | |
| SALMONN_7B,15.4,10.4 | |
| SeaLLMs-Audio-7B,66.2,67.6 | |
| cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct,78.8,67.0 | |
| cascade_whisper_large_v3_llama_3_8b_instruct,62.800000000000004,69.4 | |
| phi_4_multimodal_instruct,39.0,33.4 | |