HTSC-2025: A Benchmark Dataset of Ambient-Pressure High-Temperature Superconductors for AI-Driven Critical Temperature Prediction

TL;DR

The paper introduces HTSC-2025, a comprehensive benchmark dataset of ambient-pressure high-temperature superconductors, to facilitate fair comparison and advancement of AI-based critical temperature prediction methods.

Contribution

It provides the first widely accessible benchmark dataset of high-temperature superconductors, enabling fair evaluation of AI algorithms in this field.

Findings

Includes theoretically predicted superconductors from 2023 to 2025.

Contains diverse systems like X$_2$YH$_6$, perovskite MXH$_3$, and 2D honeycomb structures.

Open-sourced at https://github.com/xqh19970407/HTSC-2025.

Abstract

The discovery of high-temperature superconducting materials holds great significance for human industry and daily life. In recent years, research on predicting superconducting transition temperatures using artificial intelligence~(AI) has gained popularity, with most of these tools claiming to achieve remarkable accuracy. However, the lack of widely accepted benchmark datasets in this field has severely hindered fair comparisons between different AI algorithms and impeded further advancement of these methods. In this work, we present the HTSC-2025, an ambient-pressure high-temperature superconducting benchmark dataset. This comprehensive compilation encompasses theoretically predicted superconducting materials discovered by theoretical physicists from 2023 to 2025 based on BCS superconductivity theory, including the renowned X$_2$YH$_6$ system, perovskite MXH$_3$ system, M$_3$XH$_8$ system, cage-like BCN-doped metal atomic systems derived from LaH$_{10}$ structural evolution, and two-dimensional honeycomb-structured systems evolving from MgB$_2$. The HTSC-2025 benchmark has been open-sourced at https://github.com/xqh19970407/HTSC-2025 and will be continuously updated. This benchmark holds significant importance for accelerating the discovery of superconducting materials using AI-based methods.