← Back to article

Equation 9 · Measuring AI Agent Reliability: What the Evidence Actually Supports

What does this equation mean?

n=100n=100

Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.

Inputs and operations100
Result or conditionn
How to read the two sides of this formula. Follow the article passage for the meaning of each quantity.

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.

Read it piece by piece

nn

Symbol n

n is part of the quantity the equation computes from the expression on the right.

Understand this part →

=

=

The expressions on both sides represent the same quantity under the stated assumptions.

Understand this part →

See an illustrated explanation →

How to interpret it

Read it with the definitions, units, and assumptions supplied by the article.

What the article says around this equation

That combinatorial form is the unbiased estimator: it uses every one of the n observed outcomes rather than discarding some of them, and it has materially lower variance than the intuitive shortcut of raising a single measured success rate to a power. The paper is explicit that the naive alternative is biased, not merely noisier, so the difference is not a technicality — using the wrong formula changes which system looks better [ 2 ] . With n=100 samples per problem, their Codex model solved 70.2% of HumanEval problems by this best-of-many-samples criterion, against 28.8% at pass@1 [ 2 ] . That gap is not a measurement error. It is the honest size of the difference between “can this model…
Read the full surrounding passage
That combinatorial form is the unbiased estimator: it uses every one of the n observed outcomes rather than discarding some of them, and it has materially lower variance than the intuitive shortcut of raising a single measured success rate to a power. The paper is explicit that the naive alternative is biased, not merely noisier, so the difference is not a technicality — using the wrong formula changes which system looks better [ 2 ] . With n=100 samples per problem, their Codex model solved 70.2% of HumanEval problems by this best-of-many-samples criterion, against 28.8% at pass@1 [ 2 ] . That gap is not a measurement error. It is the honest size of the difference between “can this model ever produce a correct solution” and “does its single best guess happen to be correct.”

Read the equation in its article →

Sources cited in the surrounding passage

These citations give research context. Read each source to check which claims it supports.

Return to Measuring AI Agent Reliability: What the Evidence Actually Supports

See this formula across 1 published context →

Browse the mathematical compendium →