Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Multi-step Reasoning on WordSort

100Accuracy

BoT

Updated 1d ago

Evaluation Results

Method	Links
BoT 2026.06		100
eMoT 2026.06		96.8
ToT 2026.06		96.4

SOTA Paper

BoT

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Dataset

WordSort

Follow for update

@wizwand_team Discord

Related Benchmarks

Multi-step Reasoning on GSM-Hard Multi-step Reasoning on SVAMP (Accuracy)Multi-step Reasoning on Game24 Multi-step Reasoning on Checkmate

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs