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 MMB benchmark leaderboard · SOTA2 Research

Research Benchmarks

Image Understanding on MMB

76.4AccuracyLaViDa-O

Updated 5mo ago

Evaluation Results

Method	Links
LaViDa-O2025.12		76.4
Sparse-LaViDa2025.12		75

SOTA Paper

LaViDa-O

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

Dataset

MMB

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 DocVQA Image Understanding on MathVerse