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

Agent Behavior Adaptation research benchmarks · SOTA2 Research

Agent Behavior Adaptation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

WebShop (WS) (test)

Qwen3-4B-Instruct

36.7Loop Ratio

17

Feb 26, 2026

AlfWorld (AW) (test)

Mistral-7B-Instruct

1,040Loop Ratio

17

Feb 26, 2026

Sudoku (Su) (test)

Qwen3-4B-Thinking

34.3Loop Ratio

17

Feb 26, 2026

FrozenLake (FL) (test)

0Loop Ratio

17

Feb 26, 2026

BlocksWorld (BW) (test)

Mistral-7B-Instruct

51Loop Ratio

17

Feb 26, 2026

Popular datasets

AlfWorld Sudoku Webshop FrozenLake BlocksWorld

Follow for updates

Join SOTA2 Contact