Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding

DeepReinforce has launched Ornith-1.0, the first open model licensed under MIT. The model includes multiple versions such as 9B Dense, 31B Dense, 35B MoE, and 397B MoE, achieving outstanding performance in programming benchmarks. Ornith-1.0 is based on pre-trained models like Gemma 4 and Qwen 3.5, both licensed under Apache 2.0, ensuring usage compatibility. Tested with LM Studio, initial results indicate strong performance in executing complex tasks.