# OpenAI o-series Reinforcement Fine-Tuning (RFT): Grader Function Design

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-openai-rft-grader-function
> Updated: 2026-08-14T00:33:56.432Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part XIV — Closed-Source API Fine-Tuning
**TLDR:** OpenAI 2024 sonu RFT açıkladı: o-series modelleri (o1, o3, o4-mini) reasoning RL ile fine-tune et. **Grader function** — model output'una sayısal score veren senin yazdığın fonksiyon (math correctness, code execution, custom rule). Verifiable domain'ler için ideal. JSON-based grader spec.