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 Performance research benchmarks · SOTA2 Research

Long-horizon Agent Performance

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

60.6Overall Score

19

May 26, 2026

64.2Overall Score

17

May 26, 2026

72.7Overall Score

13

May 26, 2026

84.6Task Score

7

May 19, 2026

CMS Medicare dataset 15-turn

75Score (out of 300)

2

Jun 26, 2026

Popular datasets

BrowseComp WideSearch CAUSAL-LOCOMO CMS Medicare dataset

Follow for updates

Join SOTA2 Contact