Skip to content

Benchmark

VBench 1.0 scene

Scores are percentages.

Models measured
9
Scores recorded
9
Sources
1
IQ weight
0.65

Score distribution

53%
Mean
54.5%
Median
7.9%
Std dev
46.1%
10th percentile
57.4%
90th percentile
37%
Min
37%67.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.65 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

#ModelScore
1Vidu Q12025-04-17· VBench data docs67.4%
2Veo 3· VBench data docs57.4%
3Sora· VBench data docs57%
4Kling V1.6· VBench data docs55.6%
5Hunyuan Video2025-05-22· VBench data docs54.5%
6LTX Video5s 768×512· VBench data docs51.1%
7Video 01· VBench data docs50.7%
8Vidu Q4· VBench data docs46.1%
9Mochi 1· VBench data docs37%

Data credits: VBench (Vchitect), MIT (licence)