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

General Utility Evaluation research benchmarks · SOTA2 Research

General Utility Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

82.7Agreement Rate

33

Jun 1, 2026

DPO mix50/1000/aug

7.33MTB Score

15

Jul 3, 2026

80Agree Score

14

Feb 26, 2026

Popular datasets

MT-Bench Chatbot MT_Bench

Follow for updates

Join SOTA2 Contact