Sophon Pillar
Last updated
Annual return [1]
24.5%
Benchmark [1] ( Nasdaq-100 )
15.1%
Excess return [1]
9.4%
Max drawdown [1]
−4.5%
Annual growth
| 2023 | 2024 | 2025 | 2026 | |
|---|---|---|---|---|
| Annual return | +55.5% | +60.4% | +48.1% | +55.9% |
| Benchmark | +39.0% | +27.0% | +20.4% | +21.9% |
| Excess returns | +16.4% | +33.4% | +27.7% | +34.0% |
| Max drawdown | -9.0% | -22.4% | -28.7% | -16.4% |
Top 10 holdings
- AMATApplied Materials22.71%
- BKNGBooking Holdings16.51%
- BKRBaker Hughes13.43%
- AVGOBroadcom Inc.13.04%
- METAMeta Platforms6.79%
- AMGNAmgen5.50%
- PEPPepsiCo5.12%
- MUMicron Technology3.54%
- MELIMercadoLibre3.35%
- NVDANVIDIA3.11%
Alpaca broker account
Training start
Assets screened on
Currency
Trading frequency
Agent description
This Sophon-3 AI model flow starts with the Nasdaq-100 as the asset universe, then runs a single AI model node: Sophon-3 Screener.
The idea is simple: narrow the universe to more interesting candidates and send the results into portfolio construction. This creates a practical workflow where screening and portfolio construction work together instead of as separate steps.
In this template, Sophon-3 Screener uses the data type Total Equity. Total Equity represents the shareholders’ residual claim on the company (assets minus liabilities); it helps describe the balance-sheet cushion and how much value is attributable to owners after debts are accounted for.
This gives the screener a balance-sheet strength lens (how much net value supports the business).
Sophon-3 Screener is an AI model node that continually learns from new market dynamics instead of relying on fixed screening rules. Its role is to filter the Nasdaq-100 toward stocks with stronger potential versus the benchmark.
1. The metrics are measured since live deployment of the agent. 21 Apr 2026