Joint Audio-Video Generation on JavisBench 1.0 (test)
0.198AV-IBMMAudio
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MMAudioSize=0.1B, Pipeline Category=T2V+V2A, Runtime=15s2026.02 | 0.198 | — | — | 6.1 | — | 0.16 | — | 0.407 | — | 0.182 | 0.15 | 0.849 | |
| JavisDiT++Size=2.1B, Pipeline Category=T2AV, Runtime=10s2026.02 | 0.198 | 141.5 | — | 5.5 | 0.282 | 0.164 | 0.316 | 0.424 | — | 0.184 | 0.159 | 0.832 | |
| JavisDiTPipeline Architecture=T2AV2025.03 | 0.197 | 204.1 | 1.4 | 7.2 | 0.263 | 0.143 | 0.302 | 0.391 | 0.801 | 0.179 | 0.154 | — | |
| JavisDiTSize=3.1B, Pipeline Category=T2AV, Runtime=30s2026.02 | 0.197 | 204.1 | — | 7.2 | 0.263 | 0.143 | 0.302 | 0.391 | — | 0.179 | 0.154 | 1.039 | |
| FoleyCftrPipeline Architecture=T2V+V2A2025.03 | 0.193 | — | — | 9.1 | — | 0.149 | — | 0.383 | 0.8 | 0.186 | 0.151 | — | |
| FoleyCSize=1.2B, Pipeline Category=T2V+V2A, Runtime=16s2026.02 | 0.193 | — | — | 9.1 | — | 0.149 | — | 0.383 | — | 0.186 | 0.151 | 0.952 | |
| See&HearPipeline Architecture=T2V+V2A2025.03 | 0.16 | — | — | 7.6 | — | 0.129 | — | 0.263 | 0.798 | 0.143 | 0.112 | — | |
| See&HearSize=0.4B, Pipeline Category=T2V+V2A, Runtime=25s2026.02 | 0.16 | — | — | 7.6 | — | 0.129 | — | 0.263 | — | 0.143 | 0.112 | 1.099 | |
| TPoSPipeline Architecture=T2A+A2V2025.03 | 0.142 | 839.7 | 4.7 | — | 0.201 | — | 0.229 | — | 0.778 | 0.129 | 0.095 | — | |
| TempoTknSize=1.3B, Pipeline Category=T2A+A2V, Runtime=20s2026.02 | 0.139 | 539.8 | — | — | 0.084 | — | 0.205 | — | — | 0.122 | 0.103 | 1.532 | |
| TempoTknPipeline Architecture=T2A+A2V2025.03 | 0.137 | 539.8 | 7.2 | — | 0.084 | — | 0.205 | — | 0.787 | 0.122 | 0.103 | — | |
| TPoSSize=1.0B, Pipeline Category=T2A+A2V, Runtime=19s2026.02 | 0.124 | 839.7 | — | — | 0.201 | — | 0.229 | — | — | 0.129 | 0.095 | 1.493 | |
| MM-DiffPipeline Architecture=T2AV2025.03 | 0.119 | 2,311.9 | 12.2 | 27.5 | 0.08 | 0.014 | 0.181 | 0.079 | 0.783 | 0.109 | 0.07 | — | |
| MM-DiffSize=0.4B, Pipeline Category=T2AV, Runtime=9s2026.02 | 0.119 | 2,311.9 | — | 27.5 | 0.08 | 0.014 | 0.181 | 0.079 | — | 0.109 | 0.07 | 0.875 | |
| ReWaSPipeline Architecture=T2V+V2A2025.03 | 0.11 | — | — | 9.4 | — | 0.123 | — | 0.28 | 0.794 | 0.104 | 0.079 | — | |
| ReWaSSize=0.6B, Pipeline Category=T2V+V2A, Runtime=17s2026.02 | 0.11 | — | — | 9.4 | — | 0.123 | — | 0.28 | — | 0.104 | 0.079 | 1.071 | |
| UniVerse-1Pipeline Architecture=T2AV2025.03 | 0.104 | 194.2 | 0.5 | 8.7 | 0.272 | 0.111 | 0.309 | 0.245 | 0.793 | 0.098 | 0.077 | — | |
| UniVerse-1Size=6.4B, Pipeline Category=T2AV, Runtime=13s2026.02 | 0.104 | 194.2 | — | 8.7 | 0.272 | 0.111 | 0.309 | 0.245 | — | 0.098 | 0.077 | 0.929 |