the labLOADING
Everyone is asking AI models where a stock is going. Almost nobody writes the answer down and checks it later. This page does exactly that: one fixed, impersonal question per ticker, recorded with the closing price that day, then scored 30 days later against what the price actually did.
You will not find today’s calls here.A fresh call is a prediction with a model’s name on it; a matured call beside its outcome is a track record. We record the first and publish only the second — which is also why this page is free, identical for every visitor, and has nothing to sign up for.
The ledger publishes no hit rate until 20 calls have been scored. So far 0 have matured. Recording started 2026-08-01.
This is the honest state of a measurement that has not run long enough yet — the same discipline as the max pain accuracy ledger, which sat empty until real settlements landed. Panel: AAPL, MSFT, NVDA, AMZN, GOOGL, META, TSLA, AMD, JPM, XOM.
Can I see what the AI says about a ticker today?
No, and that is deliberate. Today's calls are recorded but never displayed. Showing a fresh call would be publishing a recommendation with a model's name attached; showing a matured call beside what the price did is reporting a track record. Only the second is what this page is for.
How is a call scored?
Each call is a direction — higher, lower, or unclear — recorded with the closing price on the day it was asked. Thirty calendar days later we compare against the close on that date. "Unclear" is recorded and excluded from the hit rate rather than counted as a miss, because refusing to guess is a legitimate answer.
Why does the page show nothing yet?
Because nothing has matured. The ledger holds no aggregate until at least 20 calls have been scored — a hit rate computed on a handful of calls is noise wearing a percent sign. The page states what it is waiting for instead of showing a thin number.
Is this investment advice?
No. Nothing here tells anyone to do anything, no output is personalised, every visitor sees the identical page, and it is free. It is a measurement of how a class of software performs at a task people increasingly use it for.
How independent are these calls of each other?
Partially, and the honest answer matters. Calls are recorded weekly on a fixed panel of ten large-cap tickers, so consecutive 30-day windows overlap and the same market conditions influence several calls at once. Treat the sample as smaller than its raw count, and read the hit rate as directional rather than as a precise statistic.
Educational measurement, not investment advice. Nothing here is a recommendation, nothing is personalised, and a past hit rate does not predict the next call. Prices are end-of-day.
Keep going: max pain accuracy ledger · the Lab · what StockTools does not do