# Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning

arXiv: https://arxiv.org/abs/2604.27604 · HTML: https://mlsanity.com/paper/2604.27604/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 6 of 6)

- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [LAB-Bench: Measuring Capabilities of Language Models for Biology Research](https://mlsanity.com/paper/2407.10362/) (2024)
- [SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs](https://mlsanity.com/paper/2308.03349/) (2023)
- [A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications](https://mlsanity.com/paper/2506.12594/) (2025)
- [Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination](https://mlsanity.com/paper/2411.12591/) (2024)
- [SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models](https://mlsanity.com/paper/2406.09098/) (2024)

## Built on by (most cited first, 1 of 1)

- [SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context](https://mlsanity.com/paper/2607.27084/) (2026)

## Abstract (arXiv)

We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. SPUR features three key innovations: (1) Panel-Level Fine-Grained Perception: evaluating the visual perception of multimodal large language models (MLLMs) across three dimensions (numerical, morphological, and information localization) on six fine-grained panel types; (2) Cross-Panel Relation Understanding: utilizing complex images with an average of 14.3 panels per sample to evaluate MLLMs' ability to decipher intricate cross-panel relations; (3) Expert-Level Reasoning: assessment of qualitative and quantitative reasoning across five experimental paradigms to determine if models can infer conclusions from evidence as human experts do. Comprehensive evaluation of 20 MLLMs and four multimodal Chain-of-Thought (MCoT) methods reveals that current models fall significantly short of the expert-level requirements for scientific image interpretation, underscoring a critical bottleneck in AI for Science (AI4S) research.