From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models

• URL: http://arxiv.org/abs/2512.10867v2
• Date: Fri, 12 Dec 2025 11:08:08 GMT
• Title: From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models
• Authors: Zongzhao Li, Xiangzhe Kong, Jiahui Su, Zongyang Ma, Mingze Li, Songyou Li, Yuelin Zhang, Yu Rong, Tingyang Xu, Deli Zhao, Wenbing Huang,
• Abstract summary: This paper introduces the concept of Microscopic Spatial Intelligence (MiSI), the capability to perceive and reason about the spatial relationships of invisible microscopic entities.<n>To assess the potential of Vision-Language Models (VLMs) in this domain, we propose a systematic benchmark framework MiSI-Bench.<n>This framework features over 163,000 question-answer pairs and 587,000 images derived from approximately 4,000 molecular structures.
• Score: 49.40724953627119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces the concept of Microscopic Spatial Intelligence (MiSI), the capability to perceive and reason about the spatial relationships of invisible microscopic entities, which is fundamental to scientific discovery. To assess the potential of Vision-Language Models (VLMs) in this domain, we propose a systematic benchmark framework MiSI-Bench. This framework features over 163,000 question-answer pairs and 587,000 images derived from approximately 4,000 molecular structures, covering nine complementary tasks that evaluate abilities ranging from elementary spatial transformations to complex relational identifications. Experimental results reveal that current state-of-the-art VLMs perform significantly below human level on this benchmark. However, a fine-tuned 7B model demonstrates substantial potential, even surpassing humans in spatial transformation tasks, while its poor performance in scientifically-grounded tasks like hydrogen bond recognition underscores the necessity of integrating explicit domain knowledge for progress toward scientific AGI. The datasets are available at https://huggingface.co/datasets/zongzhao/MiSI-bench.

Related papers

• HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discovery [50.8841471967624]
  HiSciBench is a hierarchical benchmark designed to evaluate foundation models across five levels that mirror the complete scientific workflow.<n>HiSciBench contains 8,735 carefully curated instances spanning six major scientific disciplines.
  arXiv  Detail & Related papers  (2025-12-28T12:08:05Z)
• SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition [19.526371771173064]
  spatial cognition is fundamental to real-world multimodal intelligence, allowing models to interact with the physical environment.<n>Existing benchmarks often oversimplify spatial cognition, reducing it to a single-dimensional metric.<n>We propose a hierarchical spatial cognition framework that decomposes spatial intelligence into five progressively complex levels.
  arXiv  Detail & Related papers  (2025-11-26T15:04:18Z)
• Scaling Spatial Intelligence with Multimodal Foundation Models [90.32537840125009]
  multimodal foundation models still exhibit surprising deficiencies in spatial intelligence.<n>We take a principled approach to constructing high-performing and robust spatial intelligence.<n>SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks.
  arXiv  Detail & Related papers  (2025-11-17T18:59:33Z)
• A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers [251.23085679210206]
  Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research.<n>This survey reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate.<n>We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge.
  arXiv  Detail & Related papers  (2025-08-28T18:30:52Z)
• Holistic Evaluation of Multimodal LLMs on Spatial Intelligence [81.2547965083228]
  We propose EASI for holistic Evaluation of multimodAl LLMs on Spatial Intelligence.<n>We conduct the study across eight key benchmarks, at a cost exceeding ten billion total tokens.<n>Our empirical study then reveals that GPT-5 demonstrates unprecedented strength in spatial intelligence (SI), yet (2) still falls short of human performance significantly across a broad spectrum of SI-tasks.
  arXiv  Detail & Related papers  (2025-08-18T17:55:17Z)
• $\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models [59.125833618091846]
  We propose a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view.<n>Experiments demonstrate that $textM2$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks.
  arXiv  Detail & Related papers  (2025-08-12T05:46:47Z)
• Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models [12.945689517235264]
  We introduce Jigsaw-Puzzles, a novel benchmark consisting of 1,100 carefully curated real-world images with high spatial complexity.<n>Based on this dataset, we design five tasks to rigorously evaluate vision-language models' spatial perception, structural understanding, and reasoning capabilities.<n>The results show that even the strongest model, Gemini-2.5-Pro, achieves only 77.14% overall accuracy and performs particularly poorly on the Order Generation task.
  arXiv  Detail & Related papers  (2025-05-27T05:17:41Z)
• REO-VLM: Transforming VLM to Meet Regression Challenges in Earth Observation [58.91579272882073]
  This paper introduces a novel benchmark dataset, called textbfREO-Instruct to unify regression and generation tasks specifically for the Earth Observation domain.<n>We develop textbfREO-VLM, a groundbreaking model that seamlessly integrates regression capabilities with traditional generative functions.
  arXiv  Detail & Related papers  (2024-12-21T11:17:15Z)
• Spatial Clustering of Molecular Localizations with Graph Neural Networks [0.0]
  MIRO is an algorithm that uses neural networks to transform point clouds in order to improve clustering efficiency.<n>We show that MIRO supports simultaneous processing of clusters of different shapes and at multiple scales, demonstrating improved performance across varied datasets.<n>MIRO's robust clustering capabilities hold promise for applications in various fields such as neuroscience, for the analysis of neural connectivity patterns.
  arXiv  Detail & Related papers  (2024-11-29T17:43:57Z)
• μ-Bench: A Vision-Language Benchmark for Microscopy Understanding [43.27182445778988]
  Vision-language models (VLMs) offer a promising solution for large-scale biological image analysis. There is a lack of standardized, diverse, and large-scale vision-language benchmarks to evaluate VLMs. mu-Bench is an expert-curated benchmark encompassing 22 biomedical tasks.
  arXiv  Detail & Related papers  (2024-07-01T20:30:26Z)
• A quantitative analysis of knowledge-learning preferences in large language models in molecular science [24.80165173525286]
  Large language models (LLMs) introduce a fresh research paradigm to tackle scientific problems from a natural language processing (NLP) perspective.<n>LLMs significantly enhance our understanding and generation of molecules, often surpassing existing methods with their capabilities to decode and synthesize complex molecular patterns.<n>We propose a multi-modal benchmark, named ChEBI-20-MM, and perform 1263 experiments to assess the model's compatibility with data modalities and knowledge acquisition.
  arXiv  Detail & Related papers  (2024-02-06T16:12:36Z)
• Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science [0.0]
  We show that MACE generally outperforms alternatives for a wide range of systems. We demonstrate the capabilities of the model on tasks ranging from constrained geometry optimisation to molecular dynamics simulations. We show that MACE is very data efficient, and can reproduce experimental molecular vibrational spectra when trained on as few as 50 randomly selected reference configurations.
  arXiv  Detail & Related papers  (2023-05-23T17:01:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.