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
Linguistic Acceptability	CoLA	nlp	40	Jun 15, 2026
Paraphrase Identification	PAWS	nlp	40	Jun 15, 2026
Image Classification	OfficeHome	computer vision	40	Jun 15, 2026
Water Level Prediction	Everglades (test)	tabular time series	40	Jun 12, 2026
Indirect Prompt Injection Defense	LLM-as-judge evaluation store 15-scenario (test)	adversarial safety security