Benchmark
VBench 1.0 spatial relationship
Scores are percentages.
- Models measured
- 9
- Scores recorded
- 9
- Sources
- 1
- IQ weight
- 0.53
Score distribution
- 75.5%
- Mean
- 74.3%
- Median
- 8.6%
- Std dev
- 66.2%
- 10th percentile
- 84.3%
- 90th percentile
- 65.4%
- Min
This benchmark has a weight of 0.53 for video-generation models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Vidu Q12025-04-17· VBench data docs | 93.7% |
| 2 | Veo 3· VBench data docs | 84.3% |
| 3 | Kling V1.6· VBench data docs | 79.1% |
| 4 | Video 01· VBench data docs | 75.5% |
| 5 | Sora· VBench data docs | 74.3% |
| 6 | Hunyuan Video2025-05-22· VBench data docs | 72.1% |
| 7 | Mochi 1· VBench data docs | 69.2% |
| 8 | Vidu Q4· VBench data docs | 66.2% |
| 9 | LTX Video5s 768×512· VBench data docs | 65.4% |
Data credits: VBench (Vchitect), MIT (licence)