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

Puzzle Solving research benchmarks – Page 2 · SOTA2 Research

Puzzle Solving

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

PUZZLE (Human easy)

69.5Accuracy

4

Jun 4, 2026

PUZZLE (Trivial)

83.8Accuracy

4

Jun 4, 2026

3.74Average Reward

4

Feb 26, 2026

0.847Score

3

Apr 21, 2026

2.304Score

3

Apr 21, 2026

2Levels Won

3

Mar 19, 2026

Sudoku (final-step)

79.5Success Rate

2

May 15, 2026

SimpleSokoban (final-step)

23.2Success Rate

2

May 15, 2026

50.14Pass@1 Accuracy

2

May 13, 2026

8-Puzzle (test)

—

—Accuracy

0

Feb 26, 2026

Page 2 of 2

Popular datasets

Sokoban puzzle Sudoku 8-Puzzle OGBench

Follow for updates

Join SOTA2 Contact