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
6D Object Pose Tracking	EventHO3D	computer vision3d vision geometry	42	Mar 31, 2026
Anomaly Detection	Annthyroid	tabular time series	42	Jun 30, 2026
Risk Prediction	Apollo Simulator Safety Properties Evaluation Scenarios	tabular time series	42	Mar 30, 2026
Out-of-Distribution Detection	CIFAR-100 ID Average OOD	computer visiontabular time series	42	Apr 28, 2026
Science and Knowledge Question Answering	Science and Knowledge Aggregate: SciQ, ARC-Easy, MedMCQA (test)	nlpllm chat instruction