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
Machine Unlearning	TOFU (1%)	adversarial safety security	59	Jun 25, 2026
Question Answering	WebQSP	nlp	59	Jul 2, 2026
Image Super-Resolution	Set14 x2 scale (test)	computer vision	59	May 26, 2026
Semantic Segmentation	GlaS	computer vision	59	Mar 11, 2026