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
Word alignment	Buckeye	nlp	45	Jul 9, 2026
Mathematical Reasoning	MATH 500	llm chat instructionnlp	45	Jun 17, 2026
Mathematical Reasoning	Math-Synth	llm chat instructionnlp	45	Jun 17, 2026
Traffic Prediction	PeMS04 to PeMS08	tabular time series	45	Jun 16, 2026
Conformal Prediction	Example 2 5-class data (a=0.5, Easy Bin, r* > 0.5) synthetic (test)	tabular time series	45	Jun 16, 2026