MathVerse

Dataset Card for MathVerse Dataset Description Paper Information Dataset Examples Leaderboard Citation Dataset Description The capabilities of Multi-modal Large Language Models (MLLMs) in visual math problem-solvingremain insufficiently evaluated and understood. We investigate current benchmarks to incorporate excessiv

Papers using MathVerse (12)

TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding2026Mmformalizer: Multimodal Autoformalization In The Wild2026OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models2026Beyond Single-Sample: Reliable Multi-Sample Distillation for Video Understanding2026GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solving2026Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning2025VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search2025AStar: Boosting Multimodal Reasoning with Automated Structured Thinking2025MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale2024