Text-to-Audio Instruction Following on AudioTime
98Ordering AccuracyStable Audio Open
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Stable Audio Open2026.06 | 98 | 3.07 | 1.46 | 53 | |
| MMAudio2026.06 | 98 | 3.33 | 1.54 | 50 | |
| Stable Audio Open2026.06 | 98 | 3.07 | 1.46 | 53 | |
| MMAudio2026.06 | 98 | 3.33 | 1.54 | 50 | |
| AudioLDM2026.06 | 97 | 3.41 | 1.54 | 41 | |
| AudioLDM2026.06 | 97 | 3.41 | 1.54 | 41 | |
| AudioLDM-22026.06 | 96 | 3.4 | 1.64 | 54 | |
| AudioLDM-22026.06 | 96 | 3.4 | 1.64 | 54 | |
| AudioGen2026.06 | 91 | 3.73 | 1.58 | 54 | |
| AudioGen2026.06 | 91 | 3.73 | 1.58 | 54 | |
| Tango 22026.06 | 86 | 3.7 | 1.52 | 61 | |
| Tango 22026.06 | 86 | 3.7 | 1.52 | 61 | |
| Audio-Oscar2026.06 | 79 | 1.44 | 1.08 | 54 | |
| Make-An-Audio22026.06 | 76 | 3.4 | 1.42 | 56 | |
| Make-An-Audio 22026.06 | 76 | 3.4 | 1.42 | 56 | |
| AudioX-Turbo2026.06 | 63 | 1.8 | 0.96 | 66 | |
| AudioX-Base2026.06 | 58 | 1.71 | 0.89 | 70 | |
| AudioX2026.06 | 34 | 1.3 | 0.74 | 81 |