TL;DR
Get business pricing on monitors, keyboards and dev gear
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
FirstQFM reports that its quantum reservoir computing system outperformed the classical models in a test of next-day forecasts across 43 anonymized assets and 600 out-of-sample periods. The reported gains come from a company-described evaluation; independent replication, trading costs and other details needed to judge real-world performance are not established in the supplied material.
FirstQFM said its quantum reservoir computing system outperformed the classical forecasting models it evaluated on next-day predictions for 43 anonymized financial assets across 600 out-of-sample periods. The company reported 52.02% directional accuracy and 112% higher cumulative gross portfolio profit than the strongest classical benchmark by that measure; the results are company-reported, and the supplied material does not establish independent replication.
The system combined a proprietary foundation model with quantum reservoir computing, with quantum features generated on Rigetti Computing’s Cepheus-1-108Q system. FirstQFM reported 52.02% directional accuracy and a macro-F1 score of 51.76%, the highest among the models in the evaluation. The comparison set included classical machine-learning and statistical models, as well as time-series foundation models Chronos-2, Granite TTM-R2 and Toto 2.0.
For an equally weighted portfolio spanning all 43 assets, FirstQFM reported 112% higher cumulative gross profit and loss than the classical benchmark with the highest gross P&L. Its annualized Sharpe ratio was 1.22, compared with 1.02 for the highest-scoring classical benchmark on that measure. FirstQFM also said its system exceeded 50% directional accuracy on 36 assets and produced positive gross P&L on 41.
A separate five-asset portfolio, selected using what FirstQFM described as a historical diversification methodology, had a reported annualized Sharpe ratio of 1.73 and higher directional accuracy, macro-F1 and cumulative gross P&L than the 43-asset portfolio. These are results reported by the company, not evidence in themselves that the approach will perform similarly in live trading.
Testing Quantum Forecasts on Markets
The announcement offers a financial-market test of whether quantum computing can contribute to forecasting tasks, rather than a demonstration limited to hardware performance. If the reported results hold under independent testing and realistic trading conditions, they could be relevant to asset managers and other firms evaluating machine-learning tools for financial decisions.
But the measured outcomes require careful interpretation. Gross P&L does not account, in the information provided, for trading costs, slippage or other implementation effects. A 52.02% directional accuracy score also does not by itself show that a strategy would be profitable: results depend on the size and timing of gains and losses, portfolio construction and risk. The reported Sharpe ratios offer a risk-adjusted comparison, but the source material does not provide enough detail to assess their statistical uncertainty or durability.
The result is thus a reported benchmark comparison, not proof that quantum systems generally forecast markets better than classical methods. The practical value depends on whether others can reproduce the findings and whether performance persists outside the test periods.
Products Worth Considering
Samsung Galaxy Tab S10 Lite – 6 GB RAM, 128 GB storage, up to 2 TB microSD, 10.9‑inch LCD, Gray
Apple MacBook Air 15-inch with M5 chip, 16GB Memory, 512GB SSD, and Liquid Retina Display
LG UltraGear 27GX704A-B 27-inch QHD OLED Gaming Monitor
As an affiliate, we earn on qualifying purchases.
How the Evaluation Was Set Up
According to the announcement, SW7 Group anonymized the assets and forecasting task before supplying the data to FirstQFM. The evaluation covered 600 out-of-sample periods, with data divided chronologically into training, validation and test periods. FirstQFM said model selection relied only on validation data, a design intended to keep the test period separate from selection decisions.
The classical comparison covered several types of models, including established statistical approaches and newer time-series foundation models. FirstQFM said the quantum system’s features were generated using Rigetti hardware. Its system was released in beta in July 2026, according to the source material. FirstQFM describes the underlying foundation-model technology as proprietary; the announcement does not provide an independent assessment of that claim or of the system’s commercial readiness.
FirstQFM has published a technical blog with detailed methodology and results. The supplied report identifies it as the source for further technical information, while the performance figures and interpretations in the announcement remain attributable to the companies involved in the work.
“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, Rigetti Computing CEO
Questions About Real-World Performance
The source material does not say whether an independent researcher or organization verified the evaluation, and it does not provide enough detail to judge statistical significance, confidence intervals or how sensitive the results are to the selection of assets and test periods. The number of periods alone does not establish how many were independent observations or whether performance would persist in another market environment.
It is also unclear whether the reported gross portfolio returns include any estimates for transaction costs, market impact, financing or other expenses. No net return figure, live-trading record or comparison under a shared risk and cost framework is provided in the supplied material. Details of the portfolio’s construction and the five-asset selection method would help readers evaluate whether the reported performance depends on choices made during the analysis.
The headline results should therefore be treated as FirstQFM’s account of its evaluation. They do not establish that the quantum method will outperform in future markets, or that the result comes from quantum processing rather than other differences in the system and experimental design.
Independent Testing and Method Details
The immediate next step for readers seeking to evaluate the claims is to examine FirstQFM’s technical blog and methodology, including the benchmark configurations, data splits, portfolio rules and treatment of costs. The supplied announcement does not name a planned independent replication or provide a schedule for further tests.
Additional evidence would include results reproduced by an independent team, tests on separate time periods or assets, and performance reported after realistic trading costs. FirstQFM’s system is described as beta software released in July 2026, but the announcement does not specify a new release date or disclose a customer deployment tied to these results. For now, the reported comparison is a company announcement, with its real-world implications still to be tested.
Key Questions
What did FirstQFM report?
FirstQFM said its quantum reservoir computing system achieved 52.02% directional accuracy and 51.76% macro-F1 across next-day forecasts for 43 anonymized assets and 600 out-of-sample periods. It also reported 112% higher cumulative gross P&L than the strongest classical benchmark by gross P&L.
Was the result independently verified?
The supplied material does not identify an independent verification. The results should be attributed to FirstQFM’s evaluation and announcement unless independent testing is reported.
Does the reported profit show the system would make money in live trading?
Not on its own. The figure is described as gross P&L, and the source material does not establish how trading costs, slippage or other expenses affect returns. The announcement also does not provide a live-trading record.
Which quantum hardware did the system use?
FirstQFM said its quantum features were generated on Rigetti Computing’s Cepheus-1-108Q system.
What should readers look for next?
Readers can review the technical blog cited by FirstQFM for methodology and results. Independent replication, further tests on separate data and performance after realistic trading costs would help clarify whether the reported advantage generalizes.
Source: thequantuminsider.com
