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
Semantic Segmentation	ADE20K 150 classes (val)	computer vision	35	Feb 27, 2026
Anomaly Detection	MVTec AD	tabular time series	35	Mar 17, 2026
Mathematical Reasoning	MATH500	llm chat instructionnlp	34	Jul 7, 2026
Tabular Classification and Regression	TextTab	tabular time series	34	Jun 30, 2026
Gene-expression classification	CUMIDA-42 RF-100 feature arm v2 (3 seeds x 3 folds)	bio medicaltabular time series