- Home
- Archives
- 2026
- Vol. 7 Issue 6
- Article
Development of an Evaluation Framework for Claimed Quantum Advantage in Quantum Machine Learning Using Published Benchmark Results
Authors
1 Independent Researcher, Lagos, Nigeria.
Article Information
- Published In
- Volume 7, Issue 6 (2026)
- Published Online
- November-December 2026
- Pages
- 92-99
- Article Type
- Original Article
Abstract
View PDFReports that quantum machine learning (QML) models outperform classical ones are common, but the evidence behind them is uneven. This paper develops the Quantum Advantage Evidence Framework (QAEF), a rubric that grades the evidence behind a published QML performance claim using only what the paper reports. QAEF scores seven criteria from 0 to 2:classical baseline strength, tuning parity, problem scale, hardware execution, statistical rigour, evidence that the quantum component matters, and reproducibility. Every score cites where the study reports it, and three gates stop a high total from masking a missing classical baseline, absent tuning parity or an untested quantum contribution. Applied to 15 peer-reviewed studies from 2021–2024, QAEF rated one study Strong, six Moderate, six Weak and two Unsupported. Tuning parity was the least-met criterion, and only two of eight advantage claims used strong classical baselines, against four of five parity claims. The only Strong grade went to an advantage shown on quantum rather than classical data. The full evidence sheet is given in the Appendix.
Related Articles
Share Article
*Instagram doesn't support direct link sharing from web. Copy the link and share it in your Instagram story or post.