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 research benchmarks · SOTA2 Research

General Utility

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Utility Benchmark (test)

67.5Accuracy

24

Feb 26, 2026

69.1MMMU Score

21

May 26, 2026

72.2RealWorldQA Score

21

May 26, 2026

8.1Speech Score

12

May 8, 2026

Popular datasets

MMMU RealworldQA AirBench Utility Benchmark

Follow for updates

Join SOTA2 Contact