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

Real-world perception-centric reasoning research benchmarks · SOTA2 Research

Real-world perception-centric reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Real-world perception-centric reasoning suite (test)

GLM-9B-DeltaThinker

55.53Average Score

8

May 18, 2026

GLM-9B-DeltaThinker

84.25Accuracy

8

May 18, 2026

HRBench 4K (test)

GLM-9B-DeltaThinker

80.25Accuracy

8

May 18, 2026

RealWorldQA (test)

GLM-9B-DeltaThinker

77.04Accuracy

8

May 18, 2026

Popular datasets

RealworldQA HRBench V*Real-world perception-centric reasoning suite

Follow for updates

Join SOTA2 Contact