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	HackerNews Pythia	adversarial safety security	36	Feb 26, 2026
Membership Inference Attack	DM Math Pythia	adversarial safety security	36	Feb 26, 2026
Membership Inference Attack	arXiv Pythia	adversarial safety security	36	Feb 26, 2026
Membership Inference Attack	PubMed Pythia	adversarial safety security	36	Feb 26, 2026
Membership Inference Attack	Pile CC Pythia	adversarial safety security	36