Meet Ornith-1.0, a family of open-source LLMs specialized for agentic coding.

Ornith-1.0 spans the full parameter sizes including 9B Dense, 31B Dense, 35B MoE, and 397B MoE.

Post-trained on top of gemma4 and qwen3.5, Ornith-1.0 employs a novel self-improving training strategy in which reinforcement learning is used to generate not only solution rollouts, but also the task-specific scaffolds that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model generate higher-quality solutions in agentic coding.

It achieves SOTA performance among open-source models of comparable size on coding benchmarks including:

- Terminal-Bench 2.1(77.5)
- SWE-Bench(82.4 on verified, 62.2 on pro, 78.9 on Multilingual)
- NL2Repo(48.2)
- SWE Atlas(41.2 on QnA, 42.6 RF, 39.1 TW)
- ClawEval(77.1)

All models are released under the MIT license, enabling full commercial and research use.