DeepCoder-14B开源模型发布，性能媲美o3-mini
原标题：DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level
AI 摘要
Together AI与Agentica团队联合发布了DeepCoder-14B-Preview，这是一个基于DeepSeek-R1-Distilled-Qwen-14B通过分布式强化学习微调的开源代码推理模型。该模型在LiveCodeBench上达到60.6%的Pass@1准确率，与o3-mini相当，并开源了数据集、代码、训练日志和系统优化。训练使用了24K个可验证的编程问题，在32块H100上耗时2.5周，并引入了加速2倍训练的verl-pipe系统。
正文节选
Through a joint collaboration between the Agentica team and Together AI, we release DeepCoder-14B-Preview, a code reasoning model finetuned from Deepseek-R1-Distilled-Qwen-14B via distributed RL. It achieves an impressive 60.6% Pass@1 accuracy on LiveCodeBench (+8% improvement), matching the performance of o3-mini-2025-01-031 (Low) and o1-2024-12-17 with just 14B parameters. We've open-sourced our dataset, code, training logs, and systems optimizations for everyone to progress on scaling and acc