Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.rllm-project.com/llms.txt

Use this file to discover all available pages before exploring further.

Read the full write-up

Notion blog post with full details
DeepCoder is a 14B coding model that achieves 60.6% Pass@1 on LiveCodeBench, an 8% improvement over the base model. It matches o3-mini and o1 performance on competitive programming benchmarks.

​
Results

ModelParametersLiveCodeBench Pass@1
DeepCoder14B60.6%
o3-mini (Low)Unknown~60%
o1Unknown~60%

​
Approach

Fine-tuned from DeepSeek-R1-Distill-Qwen-14B on coding competition problems using RL with code execution feedback. See the cookbooks/deepcoder cookbook (single-turn coding with hidden-test grading) for the AgentFlow-based reproducer. Released: April 2025