Open Source · MarkTechPost ·
DeepReinforce Releases Ornith-1.0: An Open-Source Coding Model Family That Learns Its Own RL Scaffolds
DeepReinforce released Ornith-1.0, an open-source coding model family based on Gemma 4 and Qwen 3.5. The models learn their own reinforcement-learning scaffold instead of using a fixed harness; the 397B flagship reports 82.4 on SWE-Bench Verified and all weights are under MIT.