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

Image Understanding on DocVQA benchmark leaderboard · SOTA2 Research

Research Benchmarks

Image Understanding on DocVQA

75.7AccuracySparse-LaViDa

Updated 5mo ago

Evaluation Results

Method	Links
Sparse-LaViDa2025.12		75.7
LaViDa-O2025.12		73.7

SOTA Paper

Sparse-LaViDa

Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models

Dataset

DocVQA

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Text-to-Image Generation on GenEval (Compositional Attributes and Latency)Visual Math Reasoning on MathVista (test)Image Understanding on MathVista Image Understanding on MMB Image Understanding on MathVerse