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
Precipitation Nowcasting	Mississippi River Basin (test)	tabular time series	60	Mar 17, 2026
Document Watermarking Robustness	Document Images (Print-scan)	computer vision	60	Mar 16, 2026
Document Watermarking Robustness	Document images Print-camera varying sizes	computer vision	60	Mar 16, 2026
Query-Answering	PersonaMem 128K context length	retrieval search ragnlp	60	Jun 1, 2026
Query-Answering	PersonaMem 32K context length	retrieval search ragnlp