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
Federated Class-Incremental Learning	CIFAR-100 Quantity-based label imbalance	computer visiontabular time series	42	Apr 13, 2026
Uncertainty Quantification	ImageNet 10	miscellaneous	42	Apr 13, 2026
Uncertainty Quantification	CIFAR10	miscellaneous	42	Apr 13, 2026
Uncertainty Quantification	FashionMNIST	miscellaneous	42	Apr 13, 2026
Fact Accuracy	Synthetic Phonebook Facts Power law Exponent beta = 1.0	llm chat instruction