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
Cross-modal Retrieval	Cross-dataset Average MIR, NUS, PAS, WIKI	multimodalretrieval search rag	32	Jul 2, 2026
Autonomous LLM training	PostTrainBench	llm chat instructionagents tool use	32	Jul 1, 2026
Secret Image Recovery	Stego Images JPEG Compression	computer visionadversarial safety security	32	Jul 1, 2026
Secret Image Recovery	Stego Images Gaussian Noise	computer visionadversarial safety security	32	Jul 1, 2026
DreamBooth-style Image Customization	Elementfire	image generation editing