Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Image Understanding on MathVista

56.9Accuracy

LaViDa-O

Updated 1mo ago

Evaluation Results

Method	Links
LaViDa-O 2025.12		56.9
Sparse-LaViDa 2025.12		56.7

SOTA Paper

LaViDa-O

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

Dataset

MathVista

Follow for update

@wizwand_team Discord

Related Benchmarks

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

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs