Emotion Recognition on IEMOCAP, MELD, RADESS, SAVEE Average
68.89Average AccuracyEmotionThinker
Evaluation results
| Method | Links | |
|---|---|---|
| EmotionThinkerModel Category=Omni Large Language Models2026.01 | 68.89 | |
| BLSP-EmoModel Category=Emotion Focused Speech Large Language Models2026.01 | 65.41 | |
| Kimi-AudioModel Category=General Speech Large Language Models2026.01 | 58.83 | |
| Qwen-Audio-ChatModel Category=General Speech Large Language Models2026.01 | 54.86 | |
| Qwen2-Audio-InstructModel Category=General Speech Large Language Models2026.01 | 51.14 | |
| Qwen2.5-Omni-7BModel Category=Omni Large Language Models2026.01 | 50.83 | |
| MERaLiON2Model Category=General Speech Large Language Models2026.01 | 46.09 | |
| OSUM-EChatModel Category=Emotion Focused Speech Large Language Models2026.01 | 44.04 | |
| MiniCPM-OModel Category=Omni Large Language Models2026.01 | 43.6 | |
| BLSPModel Category=General Speech Large Language Models2026.01 | 36.02 | |
| MERaLiONModel Category=General Speech Large Language Models2026.01 | 33.09 | |
| SECapModel Category=Emotion Focused Speech Large Language Models2026.01 | 32.64 | |
| Phi-4-MultimodalModel Category=Omni Large Language Models2026.01 | 32.15 | |
| DIVAModel Category=General Speech Large Language Models2026.01 | 31.87 | |
| SALMONNModel Category=General Speech Large Language Models2026.01 | 25.61 | |
| GLM-4-VoiceModel Category=General Speech Large Language Models2026.01 | 21.29 | |
| Megrez-3B-OmniModel Category=Omni Large Language Models2026.01 | 19.25 |