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 says its quantum reservoir computing system, run on Rigetti hardware, outperformed the classical models in a financial forecasting test covering 43 anonymized assets and 600 out-of-sample periods. The reported results include 52.02% directional accuracy and 112% higher cumulative gross portfolio profit than the strongest classical benchmark by profit; the figures are company-reported, and the source material does not establish independent replication or real-world trading performance.
FirstQFM said November 3 that its quantum reservoir computing system, using quantum features generated on Rigetti Computing hardware, outperformed the classical models tested in a financial forecasting evaluation. The company reported results across 43 anonymized assets and 600 out-of-sample periods, but the announcement does not establish that the findings have been independently replicated or would translate into live trading returns.
According to FirstQFM’s announcement, the system produced 52.02% directional accuracy and a 51.76% macro-F1 score, the highest results among the models included in the evaluation. The task was to forecast next-day movements. The reported comparison covered classical machine-learning and statistical models, as well as time-series foundation models including Chronos-2 from Amazon, Granite TTM-R2 from IBM, and Toto 2.0 from Datadog.
In an equally weighted portfolio covering all 43 assets, FirstQFM reported 112% higher cumulative gross profit and loss than the strongest classical benchmark by that measure. It also reported an annualized Sharpe ratio of 1.22, compared with 1.02 for the classical model with the highest Sharpe ratio. The company said its system had directional accuracy above 50% for 36 of 43 assets and positive gross portfolio P&L for 41.
The evaluation used data anonymized by SW7 Group, which supplied the forecasting task to FirstQFM. The company said training, validation and test periods were chronological, and model selection relied only on validation data. Its announcement also described a five-asset portfolio chosen using a historical diversification method; FirstQFM reported an annualized Sharpe ratio of 1.73 for that portfolio. These performance figures come from the company’s account of the evaluation.
What the Benchmark Results Could Mean
If the reported results hold under independent testing, they could add evidence that quantum computing may have practical uses in financial forecasting, a field where small differences in prediction can affect portfolio decisions. The comparison is also relevant to quantum hardware developers: financial time-series tasks provide one way to test whether current machines can contribute to useful computations, rather than only demonstrate hardware capability.
But the announcement is a benchmark result, not proof of dependable investment gains. The reported gross portfolio P&L does not by itself establish net returns after transaction costs, market impact, taxes or other trading expenses. Nor does performance over the stated test periods show how the system would behave as market conditions change. Investors and technology users should treat the figures as an initial company-reported evaluation, not as a guarantee of future results.
Products Worth Considering
Bose QuietComfort Headphones (2nd Gen), Wireless Over-Ear Noise-Cancelling Headphones, Hazelnut Taupe
DJI Osmo Mobile 8 Smartphone Gimbal with Mic Mini Transmitter, Infinity Black
Bose SoundLink Flex Bluetooth Speaker (2nd Gen) – Portable Outdoor Speaker with Hi‑Fi Audio, Waterproof and Dustproof, USB‑C, Up to 12 Hours
As an affiliate, we earn on qualifying purchases.
How FirstQFM Ran the Test
FirstQFM describes its approach as a foundation-model-based quantum reservoir computing system. The quantum features were generated on Rigetti’s Cepheus-1-108Q system, according to the announcement. SW7 Group anonymized the assets and the forecasting task before providing the data. The supplied material does not name the assets, which limits readers’ ability to judge how representative they were of particular markets.
The company said it kept the time periods in chronological order for training, validation and testing, and chose models using validation data. That design is intended to separate model selection from the final test periods. The reported model set included established statistical and machine-learning approaches and named time-series foundation models. FirstQFM released a beta version of its forecasting system in July 2026; it says the underlying technology is intended for several industries, including asset management, banking, healthcare, predictive maintenance and energy.
The announcement links to an accompanying technical blog with methodology and results. FirstQFM describes the system as commercially ready, but that characterization is the company’s own claim and is not established by the benchmark figures alone.
“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 Beyond the Reported Scores
The supplied announcement does not establish whether an independent party has reproduced the results. It also does not provide enough detail here to assess all implementation choices, the full set of metrics and uncertainty estimates, or how sensitive results were to alternative test periods. The linked technical blog may offer further methodological information, but its contents are not included in the source material provided for this report.
It is also unclear how the gross portfolio figures would change after transaction costs and execution constraints, whether the test periods represent a broad range of market conditions, and whether the advantage would persist on new data. The 43 assets are anonymized, so their identities and the degree to which the sample represents a wider investable universe are not specified. FirstQFM’s reported 112% comparison is a relative difference in cumulative gross P&L against its stated strongest classical benchmark by profit; it is not a reported annual return.
Independent Tests and Live Performance
The next useful evidence would be a detailed review of the technical methodology and results, followed by independent replication using clearly documented datasets and test procedures. Further evaluation could also report net performance after trading costs and test the system on later periods that were not used in model development.
FirstQFM’s announcement does not name a schedule for such studies or disclose a planned live-trading trial. The company has said its beta forecasting system was released in July 2026, but it has not provided customer deployment results in the supplied material. Until additional evidence is available, the reported benchmark gains remain a company-reported result from a defined evaluation.
Key Questions
What did FirstQFM report?
FirstQFM said its quantum reservoir computing system achieved 52.02% directional accuracy and produced 112% higher cumulative gross portfolio P&L than the strongest classical benchmark by profit in its test.
What data did the evaluation cover?
The company said the evaluation tested next-day forecasts across 43 anonymized assets and 600 out-of-sample periods. SW7 Group anonymized the assets and supplied the task.
Which quantum hardware did the system use?
FirstQFM said its quantum features were generated using Rigetti Computing’s Cepheus-1-108Q system.
Do the results show the system will make money in live trading?
No. The announcement reports gross backtest portfolio results, not confirmed live trading returns. It does not establish performance after costs or show that the results will persist in future markets.
Have the findings been independently verified?
The supplied source material does not report an independent replication. FirstQFM linked to a technical blog with methodology and results, but independent confirmation is not established here.
Source: thequantuminsider.com
