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
Recommendation	CiteULike (test)	tabular time series	40	Mar 4, 2026
Sequential Recommendation	CiteULike	tabular time series	40	Mar 4, 2026
Gaussian deblur	FFHQ 256 x 256	computer vision	40	Jun 30, 2026
Code-switching Ratio Calculation	Multilingual Query Set	nlp	40	Mar 4, 2026
OOD detection	ISIC Colour Chart Artefacts, Synth Dissimilar	computer visiontabular time series	40	Feb 27, 2026