# RL with Verifiable Rewards (RLVR)

> Points for a model each time a check shows it got the right answer.

**Field:** Artificial Intelligence  
**Category:** LLMs  
**Also known as:** RLVR, Reinforcement Learning with Verifiable Rewards, Verifiable Rewards

## Think of it like

It is like a quiz with an answer key. A sticker comes only when your answer matches the key.

## Definition

Reinforcement learning with verifiable rewards, or RLVR, trains a model on tasks a program can check. The model tries a problem, such as a sum or a coding task. A checker compares the final answer with the key, or runs the code's tests. It gives a reward only for a pass, so no person or reward model has to judge. The name comes from a late 2024 paper. The method is used to train reasoning models on math and code.

## Example

A model works through 1,000 math problems. A short script checks each final number against the answer key, and only the right ones earn a reward.

## Why it matters

A check by a program is cheap and hard to argue with. That makes long training on math and code possible.

## Common mistake

Using it where there is no single right answer. A script cannot mark a poem or an essay.

## Three principles

- **A checkable answer.** Math, code and puzzles.
- **A program judges.** No human rater.
- **Pass or fail.** Reward only for a match.

## Related terms

- [Reinforcement Learning from Human Feedback (RLHF)](https://learn.benibix.com/term/ai/reinforcement-learning-from-human-feedback)
- [Reward Model](https://learn.benibix.com/term/ai/reward-model)
- [Reasoning Model](https://learn.benibix.com/term/ai/reasoning-model)
- [Post-Training](https://learn.benibix.com/term/ai/post-training)
- [Test-Time Compute](https://learn.benibix.com/term/ai/test-time-compute)

## Told apart from

- [RLHF vs RLVR](https://learn.benibix.com/compare/rlhf-vs-rlvr): People think RLVR is just a new name for RLHF. It is not. In RLHF, people rank answers and a reward model learns their taste, so it can reward any kind of reply. In RLVR, a program checks the answer against a key or runs tests, so it only works where a right answer exists. RLHF shapes tone and help. RLVR trains math and code.

## Taught in

- [Post-Training and RLHF](https://learn.benibix.com/learn/ai-llms/post-training-and-rlhf): LLMs, 8/15

![A loop: the model answers a math problem, a checker compares the answer with the key, and a match sends a reward back to the model. A wrong answer gets nothing.](https://learn.benibix.com/diagrams/ai9-rlvr.svg)

---

Source: https://learn.benibix.com/term/ai/reinforcement-learning-with-verifiable-rewards
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
