Benchmark suiteResults available
VBench
Video generation quality across 16 dimensions, including subject consistency, motion, visual quality and alignment with the prompt.
73 published resultsExplore benchmark
Rather
The benchmark catalog
Find the right test.
Start with the capability you care about. Explore what each benchmark measures, which models it covers, and where the results come from.
Instruction following
Alignment between requested content and the scenes or actions a model generates.
2 suites · 86 published results
Categories group related tests. Each suite keeps its own metrics and protocols; category counts include only suites with published results.
Benchmark suiteResults available
WorldModelBench
Instruction following, physics adherence and common sense in video generation models, with native scores rather than a rescaled universal ranking.
13 published resultsExplore benchmark