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
Logistic Regression	Logistic regression d=50, K=20, epsilon=0.2 varying per-task sample size n (test)	tabular time series	102	Jul 7, 2026
Local prediction error	HAR 50% (train)	tabular time series	102	Jul 7, 2026
Out-of-Distribution Detection	CUB	computer visiontabular time series	102	Apr 24, 2026
Multimodal Reasoning	MMStar	multimodalnlp	102	Jul 7, 2026
Image Generation	Imagenet-256 latent space	image generation editing