# RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from Scientific Literature

arXiv: https://arxiv.org/abs/2512.23565 · HTML: https://mlsanity.com/paper/2512.23565/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [SciCode: A Research Coding Benchmark Curated by Scientists](https://mlsanity.com/paper/2407.13168/) (2024)
- [Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models](https://mlsanity.com/paper/2305.15074/) (2023)
- [SELFIES and the future of molecular string representations](https://mlsanity.com/paper/2204.00056/) (2022)
- [SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark](https://mlsanity.com/paper/2402.05138/) (2024)
- [MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild](https://mlsanity.com/paper/2411.11098/) (2024)
- [Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables](https://mlsanity.com/paper/2506.11375/) (2025)
- [Uni-Parser Technical Report](https://mlsanity.com/paper/2512.15098/) (2025)

## Built on by (most cited first, 4 of 4)

- [Innovator-VL: A Multimodal Large Language Model for Scientific Discovery](https://mlsanity.com/paper/2601.19325/) (2026)
- [MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models](https://mlsanity.com/paper/2608.23646/) (2026)
- [From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models](https://mlsanity.com/paper/2606.03660/) (2026)
- [LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making](https://mlsanity.com/paper/2610.19780/) (2026)

## Abstract (arXiv)

The integration of Multimodal Large Language Models (MLLMs) into chemistry promises to revolutionize scientific discovery, yet their ability to comprehend the dense, graphical language of reactions within authentic literature remains underexplored. Here, we introduce RxnBench, a multi-tiered benchmark designed to rigorously evaluate MLLMs on chemical reaction understanding from scientific PDFs. RxnBench comprises two tasks: Single-Figure QA (SF-QA), which tests fine-grained visual perception and mechanistic reasoning using 1,525 questions derived from 305 curated reaction schemes, and Full-Document QA (FD-QA), which challenges models to synthesize information from 108 articles, requiring cross-modal integration of text, schemes, and tables. Our evaluation of MLLMs reveals a critical capability gap: while models excel at extracting explicit text, they struggle with deep chemical logic and precise structural recognition. Notably, models with inference-time reasoning significantly outperform standard architectures, yet none achieve 50% accuracy on FD-QA. These findings underscore the urgent need for domain-specific visual encoders and stronger reasoning engines to advance autonomous AI chemists.