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

VisualProcessBench dataset and benchmarks · SOTA2 Research

Research Datasets

VisualProcessBench

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Step Verification

VisualProcessBench (test)

71.32Macro-F1 (DynaMath)

28

Multimodal Reasoning

VisualProcessBench Overall

54.6FEI Average

20

Reasoning Step Judgment

VisualProcessBench

74.1MMMU Score

15

Popular tasks

Multimodal Reasoning Step Verification Reasoning Step Judgment

Follow for updates

Join SOTA2 Contact