Skip to content

Benchmark

VBench 1.0 temporal flickering

Scores are percentages.

Models measured
9
Scores recorded
9
Sources
1
IQ weight
0.04

Score distribution

99.2%
Mean
99.3%
Median
0.249%
Std dev
98.9%
10th percentile
99.4%
90th percentile
98.6%
Min
98.6%99.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.04 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
1Mochi 1· VBench data docs99.4%
2Hunyuan Video2025-05-22· VBench data docs99.4%
3LTX Video5s 768×512· VBench data docs99.3%
4Vidu Q12025-04-17· VBench data docs99.3%
5Veo 3· VBench data docs99.3%
6Video 01· VBench data docs99.1%
7Vidu Q4· VBench data docs99.1%
8Sora· VBench data docs98.9%
9Kling V1.6· VBench data docs98.6%

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