CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding

arXiv:2510.09302 · cs.CV, cs.AI, cs.CL · Submitted 2025-10-10 · Read on arXiv

cs.CV, cs.AI, cs.CL

Submitted: 2025-10-10

Updated: 2026-09-13

Comments: 20 pages

Code: https://github.com/YuYingLi0/CapGeo

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 19× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• Multimodal Reasoning — 4× in this paper · explained in 5 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• International Mathematical Olympiad — 2× in this paper
• Robustness — 2× in this paper · explained in 5 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• GPT-4 Technical Report
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Qwen2.5-VL Technical Report
• Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
• OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
• SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?
• Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline
• GPT-4o System Card
• GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
• Benchmarking and Improving Detail Image Caption
• OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
• RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models
• G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
• Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
• Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
• VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
• Enhancing Advanced Visual Reasoning Ability of Large Language Models
• MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models
• LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
• Visual-RFT: Visual Reinforcement Fine-Tuning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models