We started with 11. One left in the first year. 3 more failed to graduate after 4-7 years. 5 people got postdocs. Of the 5 with postdocs, 2 left the country (one involuntarily), I left academia to work in the private sector, and one I haven't kept in touch with. So at most, 2 are on the tenure track in the US [1].
This was Rutgers - at Princeton, the ratio would be a bit better, at NJIT it would be worse. Don't even ask about podunk state.
It's a shitty career path. Unless you are fantastically good, don't waste your time.
[1] My adviser told me I could have been on the tenure track if I wanted to. Since I didn't put it to the test by applying for such jobs, I won't claim it as true.
No degree will guarantee you a job. Professional degrees (law, engn, accounting, medicine etc) will come close, if you want to work in a profession.
Every other course will just give you a better chance of getting a job, and help you perform better once you get there. A math grad can solve all kinds of problems that other people will just shrug their shoulders at. That's always useful.
Academia in general is a dangerous career path though. Too many people on the ground floor (i.e. every undergrad who can't think of a better thing than grad school), too much glamor keeping them there, very bureaucratic organizations, and a complete mismatch between work (research) and funding (students).
Physics is probably worse. In math, you are either in the game or eliminated. In physics, you can eliminated but still doing grunt work for low pay in someone's lab.
How tiny is the fraction?