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

20Q dataset and benchmarks · SOTA2 Research

Research Datasets

20Q

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Confidence Estimation

20Q

33.87Accuracy

20

Multi-step interaction

20Q

32.1Winrate

15

20Q Breeds

6.6Worst Case Interaction Length

8

20Q S128

10.8Worst Case Interaction Length

8

20Q Common

10Worst Case Interaction Length

8

Information Seeking

20Q Common weighted (test)

235.7Worst-case Weighted Payoff

8

Event Plausibility Prediction

20Q (test)

0.74AUC

6

Popular tasks

20 Questions Information Seeking Confidence Estimation Multi-step interaction Event Plausibility Prediction

Follow for updates

Join SOTA2 Contact