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

Social Interaction Evaluation research benchmarks · SOTA2 Research

Social Interaction Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

SOTOPIA-Hard GPT-4o-as-Partner

7.68Goal Score

24

Mar 4, 2026

SOTOPIA GPT-4o-as-Partner

8.75Goal Score

24

Mar 4, 2026

SOTOPIA-Hard (Self-Play)

8.06GOAL Score

24

Mar 4, 2026

SOTOPIA (Self-Play)

9.08Goal Score

24

Mar 4, 2026

9Believability Score

1

Jun 5, 2026

Popular datasets

Follow for updates

Join SOTA2 Contact