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

TL;DR

This study evaluates GPT-4o and GPT-4o-mini's ability to identify salts from dried solution drop patterns, demonstrating GPT-4o's superior classification accuracy and highlighting AI's potential in chemical pattern recognition.

Contribution

It introduces the application of OpenAI's image-enabled language models for analyzing complex crystallization patterns in dried salt solutions, showing promising classification performance.

Findings

GPT-4o classified 57% of salts correctly

GPT-4o outperformed GPT-4o-mini and random chance

AI tools can reliably identify salts from drying patterns

Abstract

When microliter drops of salt solutions dry on non-porous 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.