> ## Documentation Index
> Fetch the complete documentation index at: https://rllm-org-rllm-19-feat-renderer-parser-backend.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepScaleR

> A 1.5B model that surpasses O1-Preview by scaling RL on math reasoning

<Card title="Read the full write-up" icon="arrow-up-right-from-square" href="https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2">
  Notion blog post with full details
</Card>

DeepScaleR is a 1.5B math reasoning model that achieves **43.1% Pass\@1 on AIME**, surpassing O1-Preview. It demonstrates that small models can match frontier-level performance when RL training is scaled effectively.

## Results

| Model          | Parameters | AIME Pass\@1 |
| -------------- | ---------- | ------------ |
| **DeepScaleR** | **1.5B**   | **43.1%**    |
| O1-Preview     | Unknown    | 42.0%        |

## Approach

DeepScaleR iteratively scales Deepseek's GRPO algorithm from 8K to 16K to 24K context length for thinking, trained on top of DeepSeek-R1-Distill-1.5B on math competition problems.

See the [`cookbooks/math`](https://github.com/rllm-org/rllm/tree/main/cookbooks/math) cookbook (single-turn math with `\boxed{}` answers) for the AgentFlow-based reproducer.

**Released**: February 2025