Ornith-1.0: self-improving open-source models for agentic coding
Why CEREBRO kept it
Self-improving open-source agentic coding model exactly on-topic
The text below is an automated extraction of the article at https://github.com/deepreinforce-ai/Ornith-1, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).
Aloha! 🌺 Ornith-1.0 is a self-improving open-source models for agentic coding. Highlights: - State-of-the-Art Coding Agents: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw. - Self-Improving Training Framework: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the result
Community take
Benchmaxxed Qwen fine-tune that hallucinates heavily in practice and underperforms base Qwen models; 'self-improving' framing is marketing.
Backlinks
Appeared in 1 briefing