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
Classification	OpenML 67 datasets CC18 (10-fold cross-validation average)	computer visionnlp+3	42	May 27, 2026
Agent Behavioral Safety and Helpfulness Evaluation	ToolEmu	agents tool useadversarial safety security	42	May 27, 2026
Vessel Trajectory Prediction	Maritime-MmD+ v1 (test)	tabular time series	42	May 27, 2026
Vessel Trajectory Prediction	Maritime-MmD+ 1.0 (test)	tabular time series	42	May 27, 2026
Image Classification	UCF101	computer vision