Practice · graded on a filing
Build it from GOOGL’s latest annual filing. Every line you enter is checked by code against the filing.
Build the first row of a comps table from filings alone: derive the operating margin — filed operating income over filed revenue — for the subject and for each of the two stated peers, each from that filer's own latest annual report, then compute the peer midpoint and the subject's signed gap against it in percentage points. Every filer's margin names its own fiscal year, because the three fiscal calendars do not align and a comps row that hides that basis is not one. The walk stops at the signed difference — it compares arithmetic, never companies. Every figure you are given comes from GOOGL’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 5 of 5 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 GOOGL's model from the filed figures below (as of 2025-12-31). Derive each linked line in the unit its label names — the model must reconcile end to end.
Alphabet Inc. FY2025 10-K (period ended 2025-12-31, accession 0001652044-26-000018); peer figures cited per input: MICROSOFT CORP FY2026 10-K (period ended 2026-06-30, accession 0001193125-26-323660); AMAZON COM INC FY2025 10-K (period ended 2025-12-31, accession 0001018724-26-000004). All via SEC EDGAR. Each filer's margin uses its own fiscal year — the labels name each basis.
Educational use only — not investment advice.
Pick peers with a similar business, compute the same metrics for each from their own filings, line them up, and look at where the subject sits against the peer median. Every metric has to use the same definition and a stated period, because peers rarely share a fiscal year.
Comes up inIB first-round technicalsEquity research caseModeling test
Revenue and operating income for all three filers, as filed in each one's latest annual report and cited per figure — plus the stated peer pair, which is a fixed constant of the drill (handed to you, never graded, and not a judgment about comparability). 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.