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
Open-Domain Question Answering	NQ (Natural Questions)	nlpretrieval search rag	33	Feb 26, 2026
Image Classification	EMNIST Letters 4 (test)	computer vision	33	Feb 26, 2026
Image Classification	Original MNIST 17 (test)	computer vision	33	Feb 26, 2026
Image-to-Text Retrieval	MSCOCO (test)	multimodalretrieval search rag	33	Feb 26, 2026
Image Classification	ImageCLEF (test)	computer vision	33	Feb 26, 2026