TL;DR
Get business pricing on networking and server 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 included in a financial forecasting evaluation. The company reported 52.02% directional accuracy and 112% higher cumulative gross portfolio profit than the strongest classical benchmark by profit, but the results are company-reported and do not establish that quantum systems generally outperform classical forecasting.
FirstQFM says its quantum reservoir computing system, using features generated on Rigetti Computing hardware, outperformed the classical models tested in a financial forecasting evaluation covering 43 anonymized assets and 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 profit; the results are company-reported and do not show that quantum forecasting outperforms classical methods in general.
The evaluation examined next-day forecasts and compared FirstQFM’s foundation-model-based quantum reservoir computing system with classical machine-learning models, statistical models, and time-series foundation models. The named comparators included Chronos-2 from Amazon, Granite TTM-R2 from IBM, and Toto 2.0 from Datadog. FirstQFM reported the highest directional accuracy, at 52.02%, and macro-F1, at 51.76%, among the models evaluated.
For an equally weighted portfolio spanning all 43 assets, FirstQFM reported 112% higher cumulative gross profit and loss than the classical model with the strongest gross P&L. Its reported annualized Sharpe ratio was 1.22, compared with 1.02 for the classical benchmark with the highest Sharpe ratio. The company also said the system had directional accuracy above 50% for 36 assets and positive gross P&L for 41.
FirstQFM said SW7 Group anonymized the assets and forecasting task before supplying the data. The evaluation separated data chronologically into training, validation, and test periods, and model selection was based only on validation data, according to the company’s account. FirstQFM said its quantum features were generated using Rigetti’s Cepheus-1-108Q system. The company has published a technical blog describing its methodology and results.
What the Portfolio Results Could Mean
If the reported performance holds up under independent testing, the results could interest financial firms exploring whether quantum hardware can contribute to practical forecasting tasks. The reported edge was measured on portfolio outcomes as well as forecast classification: FirstQFM cited a higher cumulative gross P&L and Sharpe ratio than the classical comparators. Those measures are relevant to investors because they describe returns and risk-adjusted performance, although they do not by themselves establish that a strategy would make money after trading costs.
The report is also a test of a specific combination of technology: FirstQFM’s proprietary foundation-model-based approach, quantum reservoir computing, and Rigetti hardware. It should not be read as evidence that quantum computers broadly outperform classical computers in financial forecasting. The comparison covers the models, data, assets, and evaluation design used in this particular study, and its reported results have not been independently established in the supplied material.
Products Worth Considering
Apple Watch Series 8 GPS, 41mm, Midnight Aluminum Case with Midnight Sport Band (S/M)
Apple Watch Series 12 GPS 46mm Smartwatch
Amazon Kindle Scribe (32GB) with Premium Pen, Tungsten
As an affiliate, we earn on qualifying purchases.
How FirstQFM Ran the Forecast Test
FirstQFM released a beta version of its forecasting system in July 2026, according to the company’s announcement. It describes the system as built on proprietary foundation-model technology and says the platform is intended for several industries, including asset management, banking, healthcare, predictive maintenance, and energy. Those broader applications are company-stated ambitions; the results described here concern financial forecasting.
The evaluation used chronological training, validation, and test periods, a design intended to preserve the order of time-series data. SW7 Group anonymized the forecasting task and assets before sharing data with FirstQFM. The company also described a separate portfolio of five assets selected using a historical diversification methodology. It reported that this portfolio exceeded the full 43-asset portfolio on directional accuracy, macro-F1, and cumulative gross P&L, with a Sharpe ratio of 1.73. The supplied material does not give enough detail to assess how that selection method affects the comparison.
“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 chief executive
Questions About Independent Validation
The results come from FirstQFM’s announcement and its accompanying technical blog; the supplied source material does not include an independent replication or peer-reviewed study. It is not clear from the available information how the reported gross portfolio results would change after transaction costs, slippage, or other implementation constraints, or whether the evaluation period captures a range of market conditions.
The source also does not provide enough information here to determine the precise test-period dates, the full set of asset classes, or whether the benchmarks were tuned and evaluated under fully comparable resource and data conditions. Those details matter when judging whether the reported differences are robust and reproducible. The findings describe one system and one evaluation, not a general demonstration of quantum advantage across forecasting tasks.
Further Method Details and Replication
FirstQFM’s accompanying technical blog is the next source for readers seeking the company’s full methodology and reported results. Independent replication, fuller disclosure of evaluation choices, and results that account for real-world trading costs would help establish whether the reported advantage persists beyond this test.
Rigetti said empirical work can help guide improvements to quantum hardware and algorithms as the industry works toward fault tolerance. No further evaluation date or independent review was specified in the supplied material, so it remains unclear when additional results will be available.
Key Questions
What did FirstQFM report?
FirstQFM reported that its quantum reservoir computing system achieved 52.02% directional accuracy and 51.76% macro-F1, and produced 112% higher cumulative gross portfolio P&L than the strongest classical benchmark by gross P&L in its evaluation.
What data did the evaluation cover?
The company said the test covered next-day forecasts across 43 anonymized assets and 600 out-of-sample periods. SW7 Group anonymized the assets and task before providing the data.
Which classical models were compared?
FirstQFM said the comparison included classical machine-learning and statistical models, as well as time-series foundation models including Chronos-2, Granite TTM-R2, and Toto 2.0.
Do the results prove quantum forecasting is better?
No. They are results reported by FirstQFM for one system and one evaluation. The supplied material does not establish independent replication or prove that quantum systems generally outperform classical forecasting.
Where can readers find the methodology?
FirstQFM said it published a technical blog with detailed methodology and results. The supplied source links to that blog at FirstQFM’s website.
Source: thequantuminsider.com
