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
Grayscale image JPEG compression artifact removal	LIVE1	computer vision	32	Feb 26, 2026
Video Surface Normal Estimation	Sintel	3d vision geometrycomputer vision	32	Jun 30, 2026
Holistic Social Debiasing Assessment	Alignment and Bias Level Evaluation (ABLE)	llm chat instructionadversarial safety security	32	Feb 26, 2026
Zero-shot Image-Text Retrieval	Flickr	multimodalretrieval search rag	32