Glossary · Term

best-of-n

← all terms

Definition

Plain language

Running a model several times on the same task and keeping the single best attempt according to some scorer.

As stated in the literature

An inference-time strategy that samples N candidate outputs and selects the highest-scoring one under a verifier or reward signal; distinct from majority voting, which aggregates by consensus rather than picking a single best.

Also called: Best-of-N, best-of-many, Best-of-15

Why it matters: It's a simple way to boost answer quality at the cost of extra compute, as long as you have a reliable way to score the candidates.

For example, you might ask a model to write the same function five times and keep only the version that passes all the tests.

Heard on the show

“Best-of-N — generate five, pick one.”
Episode 170 — When a One-Liner Beats Your Agent's Clever Verification Logic

Mentioned in 3 episodes

  1. 170
    When a One-Liner Beats Your Agent's Clever Verification Logic
  2. 119
    Beating Reinforcement Learning Without Ever Touching the Model's Weights
  3. 107
    How a Market of Crippled AI Agents Outscored One Unrestricted Model

Related terms