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
Medical Image Segmentation	BUSI	bio medicalcomputer vision	143	Jun 30, 2026
Long-context understanding	LongBench	llm chat instructionnlp	143	Jun 25, 2026
Membership Inference Attack	Flickr	adversarial safety security	142	Apr 2, 2026
Text Retrieval	MSCOCO	retrieval search rag	142	Apr 21, 2026
Monocular Depth Estimation	Sintel	3d vision geometrycomputer vision	142	Jul 7, 2026