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

Long-Horizon Agent Tasks research benchmarks · SOTA2 Research

Long-Horizon Agent Tasks

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AppWorld (test)

86.2Easy Success Rate (SR)

6

Apr 30, 2026

Mind2Web (test)

53.8Element Accuracy

6

Apr 30, 2026

Popular datasets

Mind2Web AppWorld

Follow for updates

Join SOTA2 Contact