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
Winograd Schema Challenge	WinoGrande	nlp	39	May 8, 2026
Federated Backdoor Defense	CIFAR-10	adversarial safety security	39	May 7, 2026
Membership Inference Attack	newsQA	adversarial safety security	39	May 7, 2026
Membership Inference Attack	SQuAD	adversarial safety security	39	May 7, 2026
Object Manipulation	OGBench cube play (Double)	robotics embodied aicomputer vision	39	Jun 9, 2026
Hallucination Detection