← All parts of this equation

Equation 2 · Part 4 · What Claude's Capability Evaluations Actually Measure

Symbol b

p(t)=11+exp⁡(a+blog⁡t),p(t) = \frac{1}{1 + \exp\left(a + b \log t\right)},
bb

What this part means

b occurs below the fraction bar. The quantity above the bar is divided by this expression; zero is excluded as a denominator.

Its job in the formula

b occurs below the fraction bar. The quantity above the bar is divided by this expression; zero is excluded as a denominator.

The passage around this formula

…it plainly exposes the assumption it rests on. For a task of human-expert duration t , METR fits a logistic curve to the model’s observed success rate across many tasks of varying length: p(t)=11+exp⁡(a+blog⁡t)p(t) = \frac{1}{1 + \exp\left(a + b \log t\right)}. with b > 0 , so predicted success falls as human-equivalent task length grows. The reported time horizon TxT_x at success level x is then the duration at which the fitted curve crosses that threshold, i.e. the t solving p(t) = x . Two things follow directly from this formulation that a single reported…

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value guide →

See this notation across published equations →

Sources cited in the article section

These citations provide research context; check each source for the exact claim it supports.