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
Membership Inference Attack	IMDB	adversarial safety security	32	Apr 24, 2026
Membership Inference Attack	SST	adversarial safety security	32	Apr 24, 2026
Membership Inference Attack	Yelp	adversarial safety security	32	Apr 24, 2026
Membership Inference Attack	CoLA	adversarial safety security	32	Apr 24, 2026
Scientific Reasoning	ARCc	nlp	32	Apr 23, 2026
Reading Comprehension	Belebele c