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 its quantum reservoir computing system, using Rigetti hardware, outperformed the classical models 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 that measure; the results are company-reported and do not establish performance in live trading.
FirstQFM said its quantum reservoir computing system, generating quantum features on Rigetti Computing hardware, outperformed the classical forecasting models tested in an evaluation across 43 anonymized financial 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 model by that measure, but the results come from a company-described evaluation, not evidence of returns in live trading.
The evaluation tested next-day forecasts and compared FirstQFM’s foundation-model-based quantum system with classical machine-learning and statistical models, as well as time-series foundation models. The classical systems named in the report included Amazon Chronos-2, IBM Granite TTM-R2 and Datadog Toto 2.0. FirstQFM said its system recorded 51.76% macro-F1, also the highest among the models evaluated.
For an equally weighted portfolio spanning all 43 assets, FirstQFM reported 112% higher cumulative gross profit and an annualized Sharpe ratio of 1.22. The highest Sharpe ratio among the classical benchmarks was 1.02. These are separate performance measures; the reported profit figure is gross, and the supplied material does not give the absolute profit amount or establish net returns after trading costs.
The report also gives results by asset: the system had directional accuracy above 50% for 36 of 43 assets and positive gross profit for 41. FirstQFM separately described a five-asset portfolio selected using a historical diversification method; it reported that this portfolio exceeded the full 43-asset portfolio on directional accuracy, macro-F1 and cumulative gross profit, with a Sharpe ratio of 1.73. The company’s technical blog contains the detailed methodology and results.
What the Benchmark Could Show
The results matter because they offer a concrete test of whether quantum computing can contribute to a financial forecasting task, rather than only demonstrating a hardware or algorithm in isolation. The reported gains span both forecast scores and portfolio measures, giving researchers and finance firms specific results to examine and attempt to reproduce.
But the scope is limited to the evaluation described by FirstQFM. Historical, out-of-sample performance is not a guarantee of future performance, and gross portfolio profit does not account for all the costs and constraints of trading. The announcement therefore points to a potentially useful research result, not proof that quantum forecasting is ready to improve investment outcomes in routine use.
Products Worth Considering
Bose TV Speaker (2nd Gen) Compact Soundbar
DJI Osmo Mobile 8 Smartphone Gimbal with Mic Mini Transmitter, Infinity Black
Anker SOLIX C300 Portable Power Station, 288Wh
As an affiliate, we earn on qualifying purchases.
How the Test Was Set Up
According to FirstQFM, SW7 Group anonymized the assets and forecasting task before supplying data. The evaluation divided observations into chronological training, validation and test periods, and model selection was based only on validation data. The company said quantum features were generated using Rigetti’s Cepheus-1-108Q system.
FirstQFM released a beta version of its foundation-model-based QRC forecasting system in July 2026, according to the announcement. The company describes the underlying technology as proprietary and says it is intended for several industries. The supplied material does not independently verify those broader commercial claims; the reported benchmark concerns financial forecasts on the stated asset set and test periods.
“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
Limits of the Reported Results
The announcement does not specify the absolute portfolio profit, the full forecast-period dates, or the detailed trading assumptions needed to assess how the gross results might translate into net returns. The source material also does not report an independent replication, statistical uncertainty estimates, or performance on live trades. It is not clear from the summary how sensitive the findings are to different fees, portfolio rules or market conditions.
Although the company describes the comparison as involving state-of-the-art classical benchmarks, the results establish only how the tested systems performed under the stated evaluation. They do not show that quantum methods generally outperform classical forecasting, or that the reported ranking would hold on other data or in future markets.
The Next Test for Quantum Forecasting
FirstQFM has published a technical blog with the detailed methodology and results, which provides the next material for scrutiny. Readers will be able to assess the model comparisons and evaluation design against the summary in the announcement. The supplied information does not identify a scheduled independent replication or a forthcoming live-trading trial.
Further evidence would need to show whether the reported performance can be reproduced on new data and maintained after trading costs and operational constraints. Until those tests are available, the announcement remains a benchmark report from FirstQFM and its project partners, not a confirmed demonstration of real-world investment returns.
Key Questions
What did FirstQFM report?
FirstQFM said its quantum reservoir computing system achieved 52.02% directional accuracy and 51.76% macro-F1, outperforming the classical models it evaluated on next-day forecasts across 43 anonymized assets and 600 out-of-sample periods.
Which quantum hardware was used?
The company said it generated quantum features using Rigetti Computing’s Cepheus-1-108Q system.
Does the 112% figure mean 112% net investment returns?
No. FirstQFM reported 112% higher cumulative gross portfolio profit than the strongest classical benchmark by gross profit. The supplied material does not provide an absolute profit amount or establish net returns after trading costs.
Were the results independently verified?
The source material describes an evaluation reported by FirstQFM and does not identify an independent replication. The company said its technical blog contains the detailed methodology and results.
What remains unproven?
The report does not establish that the system will keep its performance on new data or in live trading, or that quantum forecasting generally beats classical methods. Results after fees and other practical trading constraints are also not specified.
Source: thequantuminsider.com
