Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 indexed

Task	Dataset	Domain	Results	Last Update
Classification	CelebA	computer visionnlp+3	197	May 8, 2026
Video Action Recognition	Kinetics-400	computer vision	197	May 11, 2026
3D Human Pose Estimation	Human3.6M	3d vision geometrycomputer vision	197	Jun 30, 2026
Out-of-sample random-X regression	Spiked covariance model d/N = 0.9, noise = 1 synthetic (out-of-sample)	tabular time series