Same name, scored again.
Night Grade watches a model name. Each night the same private questions go to every name you turned on. The replies are scored against known answers. This page receives the percents.
The questions are not on this server. A provider that keeps your prompts only sees that night’s draw, and the draw changes.
Five benches
Facts. Short recall with one stable answer.
Reasoning. Arithmetic, rates, ages, and clock angles. Some of these are written fresh each night.
Coding. The model reads a short Python program and says what it prints. The night script runs that program itself. It does not run the model’s reply.
Instructions. The reply has to match the shape that was asked for. A new token is added each night so the line cannot be memorized.
Adversarial. Wording traps and confident mistakes. Easy facts can stay perfect while this bench falls. Those items carry more weight, and they are not printed here.
The pool is about two hundred private items. A night uses a slice of them, weighted toward items that have been failing. The whole pool is not sent, and it is not published.
When a card says Fell
The first 14 nights are a baseline. After that, the last 7 nights are compared with the 7 before them.
The card says Fell when the week is down by 8 points, or one bench is down by 15. The numbers on the board are the ones in force if you change them in the night script.
If every watched name falls together, the card says the others fell too. That is a hard draw, or all of them changed. One name falling while the rest hold is the silent swap: the name on the API stayed, and the answers got worse.
A night that comes back empty, or an id the provider rejects, is not stored as a low score. The card keeps the earlier line and shows the error.
What is posted
Model name, provider, the week’s score, the five benches, a line of up to 30 nights, and the alert sentence. Not the questions. Not the replies. Not the API keys.
The keys stay on the machine that runs the night script. If you set a mailbox on this host, a new fall can also send mail. The mail is the same sentences, still without the questions.
See a drawn card before a real night has been posted.