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 Reasoning research benchmarks · SOTA2 Research

Long-horizon Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

EXPLORE-Bench Full

65.59Sobj Score

6

Jul 3, 2026

EXPLORE-Bench Long

59.37Sobj Score

6

Jul 3, 2026

EXPLORE-Bench Medium

66.71Sobj Score

6

Jul 3, 2026

EXPLORE-Bench Short

66.12Object Score

6

Jul 3, 2026

73.9Average Score

6

May 12, 2026

Checkers Jumping

Lookahead-Enhanced Atomic Decomposition

100Performance (n=13)

3

Mar 10, 2026

Checkers Jumping

Lookahead-Enhanced Atomic Decomposition

100Performance (n=11)

3

Mar 10, 2026

Popular datasets

EXPLORE-Bench Checkers Jumping Locomo

Follow for updates

Join SOTA2 Contact