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
Boolean Question Answering	BoolQ	nlp	57	May 21, 2026
Self-optimization	OPT-BENCH-ML	llm chat instruction	57	May 12, 2026
Classification	ADNI (test)	computer visionnlp+3	57	Jun 30, 2026
Out-of-Distribution Detection	CelebA In-Distribution	computer visiontabular time series	57	May 13, 2026
Question Answering	MuSiQue	nlp	57	Jul 8, 2026
Animal Vocalization Classification