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
Image Classification	CIFAR-100	computer vision	144	Jul 3, 2026
Adversarial Attack Transferability	LLM Cascades Evaluation Set Open-Source Models	adversarial safety securitycomputer vision	144	May 19, 2026
Ultrasound Image Denoising	In vivo Ultrasound 2 sub-apertures	computer visionbio medical	144	May 14, 2026
Multi-Object Tracking	MOT Simulation	computer vision	144	Apr 27, 2026
Image classification	QMNIST (non-IID)	computer vision