AI benchmark leaderboards – Page 228 · SOTA2 Research

SOTA2 Research · benchmarks

Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

Benchmarks

309,131 indexed

Task	Dataset	Domain	Trend	Results	Last Update
Long-form Video Understanding	EgoSchema	computer vision		69	Jun 16, 2026
Open Vocabulary Semantic Segmentation	PASCAL Context Context60 with background	computer vision		69	Mar 25, 2026
Class-Incremental Learning	CIFAR-100 B0_Inc10	computer visiontabular time series		69	Jun 25, 2026
Jailbreak Attack	Behaviours	adversarial safety security		69	Feb 26, 2026
Person Re-Identification	CUHK03 NP (test)	computer vision

Few-shot Image Classification	11 datasets average CLIP-based (ImageNet, Caltech101, OxfordPets, StanfordCars, Flowers102, Food101, FGVCAircraft, SUN397, DTD, EuroSAT, UCF101)	computer vision		69	Mar 26, 2026