TL;DR
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
FirstQFM reported that a quantum reservoir computing system running on Rigetti hardware outperformed the classical models in its evaluation of next-day forecasts for 43 anonymized financial assets. The company reported 52.02% directional accuracy and 112% higher cumulative gross portfolio profit than the strongest classical benchmark by profit; independent replication and key financial assumptions have not been established in the supplied material.
FirstQFM said its quantum reservoir computing system outperformed the classical models tested in a next-day financial forecasting evaluation covering 43 anonymized assets and 600 out-of-sample periods. The company reported 52.02% directional accuracy and cumulative gross portfolio profit 112% higher than the strongest classical benchmark by profit, in a result that could draw interest from finance and quantum-computing researchers but has not been independently verified in the supplied material.
The evaluation used FirstQFM’s foundation-model-based quantum reservoir computing (QRC) system, with quantum features generated on Rigetti Computing’s Cepheus-1-108Q hardware. FirstQFM said the system achieved 51.76% macro-F1 as well as the highest directional accuracy among the models evaluated. Its comparison set included classical machine-learning and statistical models, along with time-series foundation models such as Chronos-2 from Amazon, Granite TTM-R2 from IBM and Toto 2.0 from Datadog.
For an equally weighted portfolio of all 43 assets, FirstQFM reported 112% higher cumulative gross profit and an annualized Sharpe ratio of 1.22. It reported a highest classical benchmark Sharpe ratio of 1.02. Across assets, the system recorded directional accuracy above 50% for 36 and positive gross profit for 41, according to the company. These are results from the reported test, not evidence of returns from live trading; the source material does not provide net returns after transaction costs or other implementation expenses.
FirstQFM also described a separate five-asset portfolio chosen using a historical diversification methodology. The company said it scored higher than the full 43-asset portfolio on directional accuracy, macro-F1 and cumulative gross profit, with a reported annualized Sharpe ratio of 1.73. That portfolio is a distinct result and should not be conflated with the headline comparison across all 43 assets.
What the Forecast Results Could Mean
The report offers a testable example of quantum hardware being used in a practical forecasting task, rather than a result stated only in terms of computing performance. If the reported advantage holds up under independent testing and realistic trading conditions, it could motivate further work on whether quantum reservoir methods add value to financial models.
For investors and financial firms, the distinction between a backtest and deployable performance is consequential. The reported measures describe forecasts and gross portfolio outcomes within a particular evaluation. They do not establish that a customer could reproduce the results in live markets, or that the system would remain profitable after fees, market impact, risk limits and operational constraints. The findings are therefore an early benchmark claim, not a demonstrated investment product outcome.
The comparison also matters to quantum-computing developers because it tests a system on a named commercial quantum processor. Rigetti CEO Subodh Kulkarni said empirical studies like this help probe the capabilities and limits of current quantum computers and inform hardware development. The report does not, however, isolate how much of the measured performance came specifically from quantum processing rather than other components of FirstQFM’s system.
Products Worth Considering
Apple Watch Series 12 GPS 46mm Smartwatch
Apple Watch Series 8 GPS, 41mm, Midnight Aluminum Case with Midnight Sport Band (S/M)
Bose QuietComfort True Wireless Earbuds with Active Noise Cancellation, Black
As an affiliate, we earn on qualifying purchases.
How FirstQFM Ran the Evaluation
According to the report, SW7 Group anonymized the assets and forecasting task before supplying data to FirstQFM. The company said the evaluation used chronological training, validation and test periods, and that model selection relied only on validation data. A chronological split can help limit the use of future information when evaluating forecasts, although the supplied source does not include enough detail to independently assess every methodological choice.
FirstQFM released a beta version of its foundation-model-based QRC forecasting system in July 2026. The company describes the underlying technology as proprietary and says it is intended for use in fields including asset management, banking, healthcare, predictive maintenance and energy. Its characterization of the system as commercially ready is a company claim; the reported financial evaluation alone does not establish performance across those other sectors.
The technical blog accompanying the announcement contains the detailed methodology and results, according to FirstQFM. SW7 Group’s Head of Risk, Oleksiy Kondratyev, said the results show an opportunity to develop quantum machine-learning solutions for quantitative finance. That statement reflects SW7’s view of the experiment, not an independent replication of its findings.
“Empirical work such as FirstQFM’s helps us probe the capabilities and limits of today’s quantum computers, while helping hardware teams understand which improvements matter most.”
— Subodh Kulkarni, CEO of Rigetti Computing
Questions About Reproducibility and Trading
The findings are presented by FirstQFM, and the supplied material does not report an independent replication or peer-reviewed assessment. Although it says a technical blog provides detailed methodology, the announcement does not establish whether another team has reproduced the results on the same data or a separate dataset.
Several details needed to judge practical significance are not specified in the source material, including the exact dates covered by the 600 test periods, the full model configurations, uncertainty estimates and whether the test data were used only once. The company reports gross portfolio profit, but the supplied account does not say how transaction costs, slippage, liquidity, taxes or other trading constraints affect the comparison. It is also unclear how robust the results would be across different market conditions.
The reported Sharpe ratios and accuracy figures are therefore best treated as company-reported benchmark results. The source does not establish that the system has generated live returns, that the advantage is statistically reliable, or that quantum processing itself caused the difference.
What to Watch in Follow-Up Testing
FirstQFM has made its accompanying technical blog the next source for scrutiny, with the company saying it contains the evaluation methodology and detailed results. Readers can look for fuller descriptions of the asset set, test-period dates, model settings, portfolio construction and calculation of reported metrics.
The key next step would be independent testing, preferably on data and periods not used in model development, alongside comparisons that include trading costs and realistic execution assumptions. Further evidence could clarify whether the results persist across market regimes and whether the five-asset portfolio selection method can be applied without introducing selection bias.
No independent follow-up study, live-trading result or additional test date is specified in the supplied announcement. Until such information is available, the current development is a reported evaluation and a basis for further testing, rather than confirmation of sustained financial performance.
Key Questions
What did FirstQFM report?
FirstQFM said its quantum reservoir computing system achieved 52.02% directional accuracy and beat the classical models tested in an evaluation of next-day forecasts for 43 anonymized assets across 600 out-of-sample periods.
What does the 112% figure refer to?
It is FirstQFM’s reported comparison of cumulative gross portfolio profit for an equally weighted portfolio of all 43 assets against the strongest classical benchmark by profit. It is not a claim about net or live investment returns.
Was the advantage independently verified?
The supplied source material does not describe an independent replication or peer-reviewed assessment. The figures should be attributed to FirstQFM’s evaluation until further verification is reported.
Which quantum hardware did the system use?
FirstQFM said it generated the system’s quantum features using Rigetti Computing’s Cepheus-1-108Q quantum system.
Does the report show the system is ready for live trading?
No. FirstQFM describes the product as commercially ready, but the reported evaluation does not establish live-market performance or account for all real-world costs and trading constraints in the material provided.
Source: thequantuminsider.com
