DownloadOrnith-1.0 is a large open-source reasoning model from DeepReinforce, built for agentic coding, tool use, and complex software engineering workflows. It is part of the Ornith 1.0 family, which includes dense and MoE models post-trained on Gemma 4 and Qwen 3.5. The model focuses on coding-agent performance across benchmarks such as Terminal-Bench, SWE-Bench, NL2Repo, OpenClaw, and ClawEval. Its training uses a self-improving reinforcement learning framework that optimizes not only solution attempts but also the scaffolds that guide those attempts, helping the model discover better search paths and produce higher-quality solutions. Ornith-1.0-397B is a reasoning model by default, generating <think> blocks before final answers, and supports tool calling through OpenAI-compatible endpoints. It can be deployed with vLLM, SGLang, Transformers, Docker, and compatible quantized local apps, and is released under the MIT license.
Features
- 397B-scale agentic coding model
- Strong results on SWE-Bench and Terminal-Bench
- Deployable with vLLM, SGLang, and Transformers
- Self-improving reinforcement learning framework
- Default reasoning mode with think blocks
- MIT-licensed and free from regional limitations
- Optimized for coding agents and software engineering
- OpenAI-compatible tool calling support
Project Samples
