Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 12, 2026

Field Identification of Matricaria chamomilla using a Portable qPCR System

Field Identification of Matricaria chamomilla using a Portable qPCR System

Published on: October 10, 2020

Benchmarking multimodal large language models for medicinal plant identification.

Yue Jiang¹, Zhenzhong Dai¹, Wen Jin¹

¹Department of Computer Science and Engineering, Shaoxing University, Shaoxing, China.

Frontiers in Plant Science

|July 11, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Spatial Transcriptomics in Breast Cancer: Advances and Applications.

Biology·2026

Same author

Serum/glucocorticoid-regulated kinase 1 (SGK1)-mediated Th17/Treg imbalance in diabetic nephropathy: mechanistic insights and therapeutic perspectives - a narrative review.

Diabetes research and clinical practice·2026

Same author

Research on Large Endothelial Cell-Derived Extracellular Vesicles in Pediatric Obstructive Sleep Apnea Syndrome.

Nature and science of sleep·2026

Same author

Causal relationships between gut microbiota, C-reactive protein levels and colorectal cancer: A Mendelian randomization study.

Medicine·2026

Same author

Field angle-independent high magnetoresistance and field angle-dependent coercivity in Fe<sub>3</sub>GaTe<sub>2</sub>/Phosphorus all-van der Waals spin valves at room temperature.

Nature communications·2026

Same author

Single-stage minimally invasive resection of synchronous left atrial myxoma and pulmonary atypical carcinoid: case report.

Journal of surgical case reports·2026

Qwen3-VL-235B achieved 90.50% accuracy in recognizing medicinal plant images, outperforming other large language models (LLMs). This study highlights the potential of AI in botanical identification, though domain-specific improvements are needed.

Area of Science:

Artificial Intelligence
Botany
Pharmacognosy

Background:

Large language models (LLMs) show promise in medical applications.
Medicinal plant recognition is crucial for drug discovery and traditional medicine.

Purpose of the Study:

To evaluate the performance of five multimodal LLMs in medicinal plant image recognition.
To compare the accuracy of GPT-4o, Llama4Scout, Gemma3-27B, Qwen3-VL235B, and DeepSeek-VL2.

Main Methods:

A dataset of 200 medicinal plant images was utilized.
Models were tested using a four-choice recognition format.
Performance was assessed based on recognition accuracy.

Main Results:

Qwen3-VL-235B achieved the highest accuracy at 90.50%.

Keywords:

identification accuracy image recognition accuracy large language models medicinal plant model evaluation

More Related Videos

Application of DNA Barcoding to Identify Medicinal Plants

Application of DNA Barcoding to Identify Medicinal Plants

Published on: November 1, 2024

Related Experiment Videos

Last Updated: Jul 12, 2026

Field Identification of Matricaria chamomilla using a Portable qPCR System

Field Identification of Matricaria chamomilla using a Portable qPCR System

Published on: October 10, 2020

Application of DNA Barcoding to Identify Medicinal Plants

Application of DNA Barcoding to Identify Medicinal Plants

Published on: November 1, 2024

GPT-4o followed with 85.00% accuracy.

Gemma3-27B, Llama4Scout, and DeepSeek-VL2 showed lower accuracies (65.50%, 58.50%, 58.00%).

Conclusions:

Multimodal LLMs demonstrate significant potential for medicinal plant identification.
Further optimization is necessary to enhance LLM accuracy in specialized botanical domains.