← Back to article

Equation 27 · OpenAI Model Systems from First Principles: Weights, Post-Training, and Inference Compute

What does this equation mean?

pk=1−(1−p)k,p_k = 1 - (1-p)^k,

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 operations1 - (1-p)^k
Result or conditionp_k
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

pkp_k

Symbol p_k

only achievable if something can identify the successful attempt.

Understand this part →

pp

Symbol p

the probability.

Understand this part →

kk

Symbol k

k 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 →
subtraction

subtraction

Subtract the following term or group from the preceding one. A leading minus marks a negative quantity.

Understand this part →

subscript

subscript

The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.

Understand this part →

superscript

superscript

A raised number can be a power. When it is a label or bound, it selects a case or the upper limit of a sum; the formula’s structure distinguishes these uses.

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

The parallel-sampling case makes the shape of the returns explicit. If a single attempt succeeds with probability p and attempts were independent, the probability that at least one of k succeeds is pk=1−(1−p)kp_k = 1 - (1-p)^k. which is concave in k and saturates quickly. Two caveats destroy any naive extrapolation from it. Attempts from one model on one prompt are strongly correlated, so realised gains fall well below this bound; and pkp_k is only achievable if something can identify the successful attempt. Without a verifier, extra samples buy candidates, not answers. This is precisely why the reasoning-effort control and the availability of parallel test-time compute are architectural facts about a…
Read the full surrounding passage
The parallel-sampling case makes the shape of the returns explicit. If a single attempt succeeds with probability p and attempts were independent, the probability that at least one of k succeeds is pk=1−(1−p)kp_k = 1 - (1-p)^k. which is concave in k and saturates quickly. Two caveats destroy any naive extrapolation from it. Attempts from one model on one prompt are strongly correlated, so realised gains fall well below this bound; and pkp_k is only achievable if something can identify the successful attempt. Without a verifier, extra samples buy candidates, not answers. This is precisely why the reasoning-effort control and the availability of parallel test-time compute are architectural facts about a product rather than mere quality dials — the GPT-5 system card describes a variant that makes use of parallel test-time compute, and states that all models were evaluated at high reasoning effort [ 1 ] .

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 OpenAI Model Systems from First Principles: Weights, Post-Training, and Inference Compute

See this formula across 3 published contexts →

Browse the mathematical compendium →