MathVision

Measuring Multimodal Mathematical Reasoning with the MATH-Vision Dataset [💻 Github] [🌐 Homepage] [📊 Main Leaderboard ] [📊 Open Source Leaderboard ] [🌿 Wild Leaderboard ] [🔍 Visualization] [📖 Paper] 🌿 NEW: MATH-Vision-Wild MATH-Vision-Wild is a photographic, real-world variant of MATH-Vision. The same testmini p

Papers using MathVision (4)

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning2025Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned2025