Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

OS Task research benchmarks · SOTA2 Research

OS Task

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Lifelong Agent Bench OS Task

78.8Success Rate (Last Epoch)

31

Jun 17, 2026

Lifelong Agent Bench (val)

74.6Success Rate

6

Feb 26, 2026

Popular datasets

Lifelong Agent Bench

Follow for updates

Join SOTA2 Contact