Evaluation of GPT-4o and GPT-4o-Mini’s Vision Capabilities for Compositional Analysis from Dried Solution Drops

2025/05/02 by Deven B. Dangi, Beni B. Dangi, Oliver Steinbock · 1 voice
Materials Science · #Machine Learning in Materials Science

paper · pdf · doi:10.1021/acsomega.5c01150

openalex publication_date 2025/05/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/15

Abstract

When microliter drops of salt solutions dry on nonporous surfaces, they form erratic yet characteristic deposit patterns influenced by complex crystallization dynamics and fluid motion. Using OpenAI's image-enabled language models, we analyzed deposits from 12 salts with 200 images per salt and per model. GPT-4o classified 57% of the salts accurately, significantly outperforming random chance and GPT-4o mini. This study underscores the promise of general-use AI tools for reliably identifying salts from their drying patterns.

Citations

• Flamingo: a Visual Language Model for Few-Shot Learning
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• Patterns Lead the Way to Far-from-Equilibrium Materials
• Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design
• Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency
• An Empirical Study of the Non-Determinism of ChatGPT in Code Generation
• GPT-4o System Card
• High-throughput robotic collection, imaging, and machine learning analysis of salt patterns: composition and concentration from dried droplet photos

Discussions

• This new paper studied whether multimodal GPT-4o can identify composition from salt stains left by drying solution drops. It got 57% correct; guessing gives 8%. Training images were provided. 1st auth [bsky, 0 points, 0 comments]