Ornith 1.0 9B
Open-source 9B-parameter language model specialized for agentic coding tasks. Post-trained on Qwen 3.5 using a self-improving RL framework that jointly learns to generate solutions and task-specific scaffolds. Achieves state-of-the-art results on SWE-bench Verified (69.4%) and Terminal-Bench 2.1 among comparable models. MIT licensed.
- Type
- Text
- Weights
- Open
- Downloads
- 968k
- Likes
- 548
- Pipeline
- text generation
- License
- mit
Model hub
ornith-ai/Ornith-1.0-9B
- Repo
- ornith-ai/Ornith-1.0-9B
- Library
- transformers
- Access
- Public
Technical tags and languages
More from DeepReinforce
8
-
1.6M DL
Ornith 1.0 35B
Text
Ornith-1.0-35B is a 35B Mixture-of-Experts reasoning model for agentic coding, post-trained on Qwen 3.5 using…
-
411k DL
Ornith 1.0 35B FP8
Text
Ornith-1.0-35B-FP8 is an FP8-quantized 35B-parameter mixture-of-experts language model specialized for agenti…
-
195k DL
Ornith 1.0 397B
Text
Ornith-1.0-397B is a 397B MoE open-source reasoning model for agentic coding, post-trained on Qwen 3.5 MoE vi…
-
292k DL
Ornith 1.0 397B FP8
Text
Ornith-1.0-397B-FP8 is DeepReinforce's open-source 397B MoE agentic coding model with FP8 quantization. Built…
-
465k DL
Ornith 1.5
Text
Ornith 1.5 is an open-source family of AI models (9B, 35B MoE, and 397B MoE) built for agentic coding, reason…
About DeepReinforce
1
DeepReinforce is an AI research startup founded by Dr. Jiwei Li, focused on using reinforcement learning to build agentic AI systems for coding and system optimization. They developed GrandCode (ranked #1 in Codeforces live competitions, beating all human grandmasters), Ornith-1.0 (open-source LLMs for agentic coding, 9B–397B parameters), and IterX (agentic code optimizer surpassing NVIDIA's cuBLAS).