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
Anomaly Detection	Head-CT	tabular time series	71	Apr 6, 2026
Vision Understanding	MMMU	computer visionmultimodal	71	Jul 7, 2026
Risk measure computation	Sparse random domains smaller scale	miscellaneous	70	Jul 7, 2026
Selective Question Answering	TriviaQA (test)	nlpretrieval search rag	70	Jul 7, 2026
Imputation	Superconductivity MNAR	tabular time series	70	Jul 7, 2026
Robustness Evaluation