Open Models Almanac
Methodspost-trainingreward modelling

single source · post-training

Deterministic task-verifier rewards

Uses deterministic, verifiable task outcomes for reward instead of an LLM judge.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reward modelling for the methods filed beside it.

Also called Deterministic verifier-based task rewards.

Filed under post-training › reward modelling