Text Quality Evaluation on OpenAudioBench English subsets (test)
7.43AlpacaEvalBaseline-AR
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Baseline-ARPrediction Type=NTP2026.02 | 7.43 | 8.27 | 615 | 642 | 7.07 | |
| Baseline-ARPrediction Type=MTP2026.02 | 7.43 | 8.27 | 615 | 642 | 7.07 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=162026.02 | 7.43 | 8.27 | 615 | 642 | 7.07 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=82026.02 | 7.43 | 8.27 | 615 | 642 | 7.07 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=42026.02 | 7.43 | 8.27 | 615 | 642 | 7.07 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=22026.02 | 7.43 | 8.27 | 615 | 642 | 7.07 | |
| VocalNet-MDMPrediction Type=MDM, Diffusion Steps=12026.02 | 7.43 | 8.27 | 615 | 642 | 7.07 | |
| MiMo-Audio2026.02 | 7.35 | 7.7 | 490 | 580 | 6.44 | |
| VocalNet-8B2026.02 | 7.12 | 7.95 | 624 | 648 | 6.95 | |
| VITA-Audio2026.02 | 6.93 | 7.43 | 427 | 523 | 5.96 | |
| Kimi-Audio2026.02 | 6.49 | 8.1 | 615 | 710 | 6.96 | |
| MiniCPM-o2026.02 | 6.13 | 7.72 | 643 | 716 | 6.86 | |
| Qwen2.5-Omni2026.02 | 6.01 | 7.9 | 589 | 688 | 6.67 | |
| GLM-4-Voice2026.02 | 5.86 | 7.74 | 495 | 556 | 6.03 | |
| SLAM-Omni2026.02 | 3.5 | 2.94 | 39 | 84 | 1.92 |