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

Agentic task solving research benchmarks · SOTA2 Research

Agentic task solving

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

90TGC

28

Feb 26, 2026

43Pass@3

9

May 11, 2026

0.462Pass@3

9

May 11, 2026

79.1Pass@3

9

May 11, 2026

92.7Pass@3

9

May 11, 2026

51.1Pass@3

9

May 11, 2026

79.7Pass@3

9

May 11, 2026

AppWorld (test-n)

81.15TGC Average

4

Apr 10, 2026

Popular datasets

AppWorld TableBench ShellOps AB-OS AB-DB

Follow for updates

Join SOTA2 Contact