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

Multi-turn decision making research benchmarks · SOTA2 Research

Multi-turn decision making

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ALFWorld (val-unseen)

94.1Success Rate

18

Mar 20, 2026

tau2-Bench held-out (test)

41.9Average Score

16

Jul 8, 2026

Popular datasets

AlfWorld tau2-bench

Follow for updates

Join SOTA2 Contact