Model,audiocaps_test,wavcaps_test Qwen-Audio-Chat,47.04090909090909,32.9364161849711 hy_whisper_local_cs,, Qwen2-Audio-7B-Instruct,40.77727272727273,33.78034682080925 whisper_large_v3,, old_models,, gemini-1.5-flash,, WavLLM_fairseq,5.5,6.901734104046243 MERaLiON-AudioLLM-Whisper-SEA-LION,39.38636363636363,34.566473988439306 MERaLiON-AudioLLM-v2-2b,35.07727272727273,31.410404624277458 MERaLiON-AudioLLM-v2-9b,36.04090909090909,35.16763005780347 MERaLiON-AudioLLM-v2-9b-asr,35.372727272727275,33.5606936416185 Qwen2.5-Omni-3B,43.69545454545454,34.70520231213873 Qwen2.5-Omni-7B,37.7,26.09248554913295 SALMONN_7B,35.24090909090909,22.520231213872833 SeaLLMs-Audio-7B,51.95909090909091,38.21965317919075 cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct,2.4545454545454546,3.8265895953757223 cascade_whisper_large_v3_llama_3_8b_instruct,2.5136363636363637,3.3179190751445087 phi_4_multimodal_instruct,33.595454545454544,28.069364161849713