# EyePCR: A Comprehensive Benchmark for Fine-Grained Perception, Knowledge Comprehension and Clinical Reasoning in Ophthalmic Surgery

arXiv: https://arxiv.org/abs/2509.15596 · HTML: https://mlsanity.com/paper/2509.15596/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 30 of 31)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Graph-Structured Representations for Visual Question Answering](https://mlsanity.com/paper/1609.05600/) (2016)
- [CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80](https://mlsanity.com/paper/2012.12453/) (2020)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [Multi-Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2407.06192/) (2024)
- [MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering](https://mlsanity.com/paper/2404.05590/) (2024)
- [HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition](https://mlsanity.com/paper/2405.10075/) (2024)
- [Advancing Surgical VQA with Scene Graph Knowledge](https://mlsanity.com/paper/2312.10251/) (2023)
- [CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models](https://mlsanity.com/paper/2406.01920/) (2024)
- [LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning](https://mlsanity.com/paper/2408.07981/) (2024)
- [OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding](https://mlsanity.com/paper/2406.07471/) (2024)
- [Automated Multi-level Preference for MLLMs](https://mlsanity.com/paper/2405.11165/) (2024)
- [OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining](https://mlsanity.com/paper/2411.15421/) (2024)
- [A Dataset for Medical Instructional Video Classification and Question Answering](https://mlsanity.com/paper/2201.12888/) (2022)
- [VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering](https://mlsanity.com/paper/2205.11501/) (2022)
- [Fine-grained Activity Recognition in Baseball Videos](https://mlsanity.com/paper/1804.03247/) (2018)
- [GP-VLS: A general-purpose vision language model for surgery](https://mlsanity.com/paper/2407.19305/) (2024)
- [LensID: A CNN-RNN-Based Framework Towards Lens Irregularity Detection in Cataract Surgery Videos](https://mlsanity.com/paper/2107.00875/) (2021)
- [VidLPRO: A underlineVideo-underlineLanguage underlinePre-training Framework for underlineRobotic and Laparoscopic Surgery](https://mlsanity.com/paper/2409.04732/) (2024)
- [CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2303.09044/) (2023)

## Built on by (most cited first, 3 of 3)

- [MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning](https://mlsanity.com/paper/2608.14015/) (2026)
- [SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark](https://mlsanity.com/paper/2604.20319/) (2026)
- [X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis](https://mlsanity.com/paper/2604.20350/) (2026)

## Abstract (arXiv)

MLLMs (Multimodal Large Language Models) have showcased remarkable capabilities, but their performance in high-stakes, domain-specific scenarios like surgical settings, remains largely under-explored. To address this gap, we develop EyePCR, a large-scale benchmark for ophthalmic surgery analysis, grounded in structured clinical knowledge to evaluate cognition across textitPerception, textitComprehension and textitReasoning. EyePCR offers a richly annotated corpus with more than 210k VQAs, which cover 1048 fine-grained attributes for multi-view perception, medical knowledge graph of more than 25k triplets for comprehension, and four clinically grounded reasoning tasks. The rich annotations facilitate in-depth cognitive analysis, simulating how surgeons perceive visual cues and combine them with domain knowledge to make decisions, thus greatly improving models' cognitive ability. In particular, EyePCR-MLLM, a domain-adapted variant of Qwen2.5-VL-7B, achieves the highest accuracy on MCQs for textitPerception among compared models and outperforms open-source models in textitComprehension and textitReasoning, rivalling commercial models like GPT-4.1. EyePCR reveals the limitations of existing MLLMs in surgical cognition and lays the foundation for benchmarking and enhancing clinical reliability of surgical video understanding models.