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

Proactive Agent Task research benchmarks · SOTA2 Research

Proactive Agent Task

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

35Pass@U-1

17

Feb 26, 2026

80.49Pass@U-1

17

Feb 26, 2026

50Pass@U-1

17

Feb 26, 2026

Popular datasets

Function-Gym Telepathy-Gym Turtle-Gym

Follow for updates

Join SOTA2 Contact