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
Class-incremental learning	CIFAR-100 (test)	computer visiontabular time series	30	May 20, 2026
Single-class Unlearning	CIFAR-10 (test)	adversarial safety security	30	Jun 17, 2026
Natural Language Understanding	Winogrande	nlp	30	May 19, 2026
Computational Pathology Classification	CPTAC k=10 (test)	bio medicalcomputer vision	30	Feb 26, 2026
Classification	CPTAC k=5 positive samples	computer visionnlp+3