# ConnectomeBench: Can LLMs Proofread the Connectome?

arXiv: https://arxiv.org/abs/2511.05542 · HTML: https://mlsanity.com/paper/2511.05542/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 16 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 3 of 3)

- [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://mlsanity.com/paper/2406.18521/) (2024)
- [Guided Proofreading of Automatic Segmentations for Connectomics](https://mlsanity.com/paper/1704.00848/) (2017)
- [RLCorrector: Reinforced Proofreading for Cell-level Microscopy Image Segmentation](https://mlsanity.com/paper/2106.05487/) (2021)

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

- [Topo-R1: Detecting Topological Anomalies via Vision-Language Models](https://mlsanity.com/paper/2603.13054/) (2026)
- [ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading](https://mlsanity.com/paper/2606.21116/) (2026)
- [Benchmarking Vision-Language Models on Synapse Detection and Proofreading in Connectomics](https://mlsanity.com/paper/2609.36492/) (2026)

## Abstract (arXiv)

Connectomics - the mapping of neural connections in an organism's brain - currently requires extraordinary human effort to proofread the data collected from imaging and machine-learning assisted segmentation. With the growing excitement around using AI agents to automate important scientific tasks, we explore whether current AI systems can perform multiple tasks necessary for data proofreading. We introduce ConnectomeBench, a multimodal benchmark evaluating large language model (LLM) capabilities in three critical proofreading tasks: segment type identification, split error correction, and merge error detection. Using expert annotated data from two large open-source datasets - a cubic millimeter of mouse visual cortex and the complete Drosophila brain - we evaluate proprietary multimodal LLMs including Claude 3.7/4 Sonnet, o4-mini, GPT-4.1, GPT-4o, as well as open source models like InternVL-3 and NVLM. Our results demonstrate that current models achieve surprisingly high performance in segment identification (52-82% balanced accuracy vs. 20-25% chance) and binary/multiple choice split error correction (75-85% accuracy vs. 50% chance) while generally struggling on merge error identification tasks. Overall, while the best models still lag behind expert performance, they demonstrate promising capabilities that could eventually enable them to augment and potentially replace human proofreading in connectomics. Project page: https://github.com/jffbrwn2/ConnectomeBench and Dataset https://huggingface.co/datasets/jeffbbrown2/ConnectomeBench/tree/main