Text-to-Audio-Video Generation on Verse-Bench
0.58MSOvi
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| OviFramework=T2AV2026.01 | 0.58 | 0.48 | 0.46 | 1.5 | 1.19 | 0.224 | 0.035 | 0.82 | 4.28 | 0.214 | |
| OviLowFramework=Unified2026.01 | 0.58 | 0.48 | 0.46 | 1.5 | 1.19 | 0.224 | 0.035 | 0.82 | 4.28 | 0.214 | |
| APOLLOFramework=Unified T2AV2026.01 | 0.48 | 0.51 | 0.59 | 1.36 | 1.06 | 0.232 | 0.028 | 0.65 | 6.79 | 0.316 | |
| MM-SonateFramework=Unified2026.01 | 0.48 | 0.56 | 0.59 | 1.43 | 1.16 | 0.242 | 0.02 | 0.76 | 6.51 | 0.27 | |
| OpenSora+FoleyGenFramework=T2V+V2A2026.01 | 0.42 | 0.44 | 0.56 | 3.69 | 3.08 | 0.212 | — | 0.92 | 2.76 | 0.159 | |
| OpenSora+See&HearFramework=T2V+V2A2026.01 | 0.42 | 0.44 | 0.56 | 2.26 | 2.97 | 0.206 | 0.337 | 0.86 | 2.85 | 0.164 | |
| OpenSora+FoleyGenFramework=Cascaded2026.01 | 0.42 | 0.44 | 0.56 | 3.69 | 3.08 | 0.212 | — | 0.92 | 2.76 | 0.159 | |
| OpenSora+See&HearFramework=Cascaded2026.01 | 0.42 | 0.44 | 0.56 | 2.26 | 2.97 | 0.206 | 0.337 | 0.86 | 2.85 | 0.164 | |
| SVGFramework=T2AV2026.01 | 0.4 | 0.41 | 0.25 | 1.55 | 3.62 | 0.08 | — | 0.72 | 4.07 | 0.206 | |
| SVGIFramework=Unified2026.01 | 0.4 | 0.41 | 0.25 | 1.55 | 3.62 | 0.08 | — | 0.72 | 4.07 | 0.206 | |
| Universe-1Framework=T2AV2026.01 | 0.2 | 0.47 | 0.25 | 1.55 | 1.25 | 0.16 | 0.18 | 0.98 | 3.92 | 0.198 | |
| Universe-1Framework=Unified2026.01 | 0.2 | 0.47 | 0.25 | 1.55 | 1.25 | 0.16 | 0.18 | 0.98 | 3.92 | 0.198 | |
| JavisDiTFramework=T2AV2026.01 | 0.18 | 0.36 | 0.22 | 1.95 | 5.17 | 0.228 | 0.256 | 0.92 | 3.94 | 0.231 | |
| JavisDiTFramework=Unified2026.01 | 0.18 | 0.36 | 0.22 | 1.95 | 5.17 | 0.228 | 0.256 | 0.92 | 3.94 | 0.231 | |
| AudioLDM+TemoTknFramework=T2A+A2V2026.01 | 0.05 | 0.12 | 0.07 | 2.05 | 2.53 | 0.229 | — | 1.15 | 2.68 | 0.137 | |
| AudioLDM+TemoTknFramework=Cascaded2026.01 | 0.05 | 0.12 | 0.07 | 2.05 | 2.53 | 0.229 | — | 1.15 | 2.68 | 0.137 |