Uploaded June 2025 | Updated November 2026, 5 hours ago
Researcher Michel Galley explores how he and fellow researchers combined new and existing data to create MathVista, an open-source benchmark for measuring the mathematical reasoning capabilities of foundation models in scenarios that involve text and images.
Read the paper: microsoft.com/en-us/research/publication/mathvista-evaluating-mathematical-reasoning-of-foundation-models-in-visual-contexts
Get the code & dataset: mathvista.github.io
Show notes: microsoft.com/en-us/research/podcast/abstracts-may-6-2024
Listen to the Abstracts series: microsoft.com/en-us/research/podcast-series/abstracts
Researcher Michel Galley explores how he and fellow researchers combined new and existing data to create MathVista, an open-source benchmark for measuring the mathematical reasoning capabilities of foundation models in scenarios that involve text and images.
Read the paper: microsoft.com/en-us/research/publication/mathvista-evaluating-mathematical-reasoning-of-foundation-models-in-visual-contexts
Get the code & dataset: mathvista.github.io
Show notes: microsoft.com/en-us/research/podcast/abstracts-may-6-2024
Listen to the Abstracts series: microsoft.com/en-us/research/podcast-series/abstracts










