Crosshair
Benchmarks
Video Understandinghigher is better

Perception Test

A diagnostic video-QA benchmark probing memory, abstraction, physics, and semantics across real-world videos. Reported as multiple-choice accuracy from a video model aligned with an LLM.

Benchmark source
Domain
Video Understanding
Metric
%
Orientation
Higher is better
Results
1

Ranking

#ModelScoreSourceStatus
1V-JEPA 2
Meta AI
84%Meta — V-JEPA 2 (arXiv:2506.09985)paperunverified