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
Object Hallucination Evaluation	MSCOCO	multimodalcomputer vision	35	Mar 31, 2026
Vision-and-Language Navigation	R2R-CE unseen continuous (val)	robotics embodied aimultimodal	35	Apr 1, 2026
Image Restoration	MiO100 AgenticIR setting (Group C)	computer vision	35	May 22, 2026
Natural Language Inference	NLI benchmarks (MNLI, QNLI, SNLI, RTE, SICK, SCITAIL) (test)	nlp	35	Jun 4, 2026
CTR Prediction	Taobao 1.68% compression	tabular time series