Compare AI investment decisions
Explore how language models allocate portfolios from the same market snapshots, then compare model runs, decisions, and backtest results side by side.
How it works
A structured workflow for comparing AI portfolio decisions.
1. Build snapshots
Each model receives the same compact view of market, price, fundamental, and earnings context.
2. Run models
Language models generate portfolio weights and rationale under the same constraints.
3. Compare results
Leaderboards and backtests make it easier to inspect model behavior across time.
What you can compare
Use the benchmark to study model decisions, not to outsource investment judgment.
Portfolio decisions
Inspect target weights, confidence, rationale, and risk notes for every model run.
Model leaderboards
Compare returns, Sharpe ratios, benchmark-relative performance, and model consistency.
Backtest history
Review how repeated model allocations would have behaved across historical rebalance periods.
Snapshot transparency
Open the structured inputs used for each run so model outputs can be judged in context.
FAQ
Short answers about the LLM Investment Benchmark.
Is this investment advice?
No. The benchmark is a research and comparison tool. You remain responsible for all investment decisions and risks.
What does the benchmark measure?
It compares how different language models transform identical market snapshots into portfolio decisions and how those decisions perform in backtests.
Why use snapshots?
Snapshots keep the input consistent across models, making comparisons more transparent and easier to audit.
Can rankings change?
Yes. Rankings depend on the period, benchmark, model set, and available data. Past performance is not a forecast.
Discover our wikifolio
QUINETICS is free to use. We partly fund the platform through partner links. If you click an advertisement, we may receive compensation. Your use of QUINETICS remains independent of that.
