DeepReinforce Releases Ornith-1.0: An Open-Source Coding Model Family That Learns Its Own RL Scaffolds

1Key Takeaways

• DeepReinforce released Ornith-1.0, an open-source coding model family built on Gemma 4 and Qwen 3.5.
• Instead of a fixed harness, the model learns its own scaffold during reinforcement learning.
• The 397B flagship reports 82.4 on SWE-Bench Verified, with all weights under the MIT license.