The Signal
FirstQFM Reports 112% Higher Portfolio P&L in Quantum Forecasting Test
FirstQFM says its quantum reservoir system produced 112% higher cumulative gross P&L than the strongest classical benchmark in a 43-asset financial forecasting evaluation. The company’s system ran on Rigetti hardware, with data supplied by SW7 Group.

FirstQFM says its quantum reservoir system delivered 112% higher cumulative gross portfolio P&L than the strongest classical benchmark in an evaluation announced Nov. 3, 2026. The equally weighted portfolio covered 43 anonymized assets, and the quantum system recorded an annualized Sharpe ratio of 1.22, compared with 1.02 for the highest-scoring classical benchmark. FirstQFM says its system also led the tested models in directional accuracy and macro-F1.
Source prnewswire.com
Results across 43 anonymized assets
For next-day forecasts across 600 out-of-sample periods, FirstQFM reported 52.02% directional accuracy and a 51.76% macro-F1 score. Those were the highest results among the models in the evaluation. Across the assets individually, the system recorded directional accuracy above 50% for 36 of 43 and positive gross P&L for 41 of 43.
A separate portfolio used five assets selected through a historical diversification methodology. FirstQFM says that portfolio had higher directional accuracy, macro-F1 and cumulative gross P&L than the full 43-asset portfolio, with an annualized Sharpe ratio of 1.73. The announcement does not give the five assets’ identities.
Rigetti hardware, SW7 data
The system generated its quantum features on Rigetti Computing’s Cepheus-1-108Q system, using financial data supplied by SW7 Group. SW7 anonymized the assets and forecasting task before providing the data to FirstQFM. The evaluation split its data chronologically into training, validation and test periods, and selected models using validation data only.
The comparison included classical machine-learning and statistical models, as well as time-series foundation models Chronos-2 from Amazon, Granite TTM-R2 from IBM and Toto 2.0 from Datadog. FirstQFM identifies those systems as part of the comparison but does not provide their individual scores in the announcement.
What Rigetti and SW7 say the test shows
Rigetti CEO Dr. Subodh Kulkarni described the evaluation as a way to examine both current machine capabilities and hardware priorities.
“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.”
Dr. Subodh Kulkarni, Chief Executive Officer, Rigetti Computing
SW7 Group Head of Risk Oleksiy Kondratyev said the company is exploring approaches to difficult quant-finance problems.
“The experimental results clearly demonstrate that QRC offers us an opportunity to build viable QML solutions with the potential to outperform classical benchmarks.”
Oleksiy Kondratyev, Head of Risk, SW7 Group
FirstQFM’s system and commercial claims
FirstQFM says it released a beta version of the forecasting system in July 2026. The company describes the system as built on proprietary foundation-model technology operating at a billion-parameter scale, and says it is developing applications for asset management, banking, healthcare, predictive maintenance and energy.
FirstQFM CEO Vish Ramakrishnan called the system commercially ready and said it had demonstrated value for enterprise customers. The announcement points readers to an accompanying technical blog for detailed methodology and results, but the benchmark figures presented here come from the company’s release.