Practice · graded on a filing
Build it from AAPL’s latest annual filing. Every line you enter is checked by code against the filing.
Size an entry enterprise value off an EBITDA proxy, split it into debt and sponsor equity at a stated leverage, grow EBITDA at a stated rate, exit at a stated multiple, and work out the multiple of invested capital and the annualized rate that multiple implies. Every figure you are given comes from AAPL’s latest annual filing and is cited below; the assumptions are handed to you and are never graded. Nothing here is a view on the company.
Match the AI
An AI model worked this exact drill and got 8 of 8 lines right. Match it.
Claude Sonnet 5, given the same filed figures and stated assumptions you see, scored by the same grader. One run, on 2026-09-28, not retried. It does arithmetic on this filing only and never forms a view on the company.
Reconcile AAPL's model from the filed figures below (as of 2025-09-27). Derive each linked line in the unit its label names — the model must reconcile end to end.
Apple Inc. 10-K (FY2025, period ended 2025-09-27), accession 0000320193-25-000079, via SEC EDGAR
Educational use only — not investment advice.
Buy the company at an entry multiple of EBITDA, fund most of the price with debt and the rest with sponsor equity, grow EBITDA over the hold, sell at an exit multiple, repay the debt, and what is left is the sponsor's equity. Divide exit equity by entry equity for the multiple of money, and annualize it over the hold for the IRR.
Comes up inPE paper LBOIB superdayModeling test
Operating income and depreciation & amortization, as filed in the latest annual report. Each cell is checked against the value the same pipeline derives from that filing, inside a small tolerance band, and the model has to reconcile end to end. There is no language model in the grade — it is arithmetic over filed figures, so it returns the same verdict every time. The correct values are not in this page: they are recomputed on the server when you submit, and your entries are read as a submission, never as the answer.
Every attempt ends in a review. Each line is marked Best, Inaccuracy, Mistake or Blunder by how far it is off, and the first line that went wrong is flagged, so an error carried through the rest of the model is fixed once, where it started.
Signed out, nothing is recorded: work it as many times as you like. Signed in, each graded attempt is saved to your account so your dashboard can track it.
Each one is built from that company's own annual filing and graded the same way.
Educational use only — not investment advice. Figures come from public SEC filings; Echelon teaches you to analyze data, it never recommends buying or selling any security.