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 Reasoning research benchmarks · SOTA2 Research

Puzzle Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Reasoning Gym (test)

17.8Avg@4

20

May 12, 2026

82Success Rate

17

May 6, 2026

Popular datasets

FrozenLake Reasoning GYM

Follow for updates

Join SOTA2 Contact